# Job Skill Enhancement System

## CORE INSTRUCTION:
You are an AI that extracts and identifies coding languages and frameworks from job descriptions. Your goal is to find ALL relevant technical skills mentioned in the job posting, even if they're mentioned in different ways or aliases.

## INPUT DATA:
{
  "job": {"job_id":4419,"title":"Development Engineer – Scientific Software Development for Wind Resource Assessment - DTU Wind","company_name":"DTU - Technical University of Denmark","description":"About the job\n\nJob Description\n\nDo you want to help accelerate the green energy transition through scientific software? \n\nWe are looking to expand our software development team with one or more scientific software developers. We are especially interested in individuals with strong domain knowledge in wind energy or Earth system sciences who are motivated to apply and grow their software development skills.\n\nAs digital tools and data platform become increasingly central to scientific research and its impact, this role plays a key part in ensuring those tools are professional, robust, and widely usable. You’ll help transform scientific insight into high-quality software used by researchers, policymakers, and industry stakeholders worldwide, turning research into practical, reproducible, scalable solutions.\n\nThe job\n\nYou will be part of a cross-functional team, developing and advancing the wind industry’s leading resource assessment software as well as large-scale datasets used for wind and renewable-energy analyses. You’ll contribute to tools like PyWAsP and Windkit, and help maintain the widely-used Global Wind Atlas and New European Wind Atlas datasets; you will also contribute through implementation of cutting-edge research results. You may also help our web applications team convert these products into web tools for dissemination, or support researchers with automating andscaling scientific workflows.\n\nCommon tasks will include:\n\n\nIntegrating new scientific methods into our Fortran and Python-based tools, and verification and validation of the resultant implementations\nSupporting large-scale geospatial global and regional wind data products\nImproving automation, testing, and documentation across the codebase\nWork with our web application team to wrap core tools in high impact web tools\nEngage with stakeholders to understand evolving scientific and technical needs\n\n\nYou don’t need to be a seasoned software developer, as we’re especially interested in scientists and engineers who bring insight into wind resource modelling, boundary layer meteorology, g, climate data, or GIS, and are eager to grow their coding and software development skills.\n\nWhat We Are Looking For\n\nWe are hiring at both Developer and Junior Developer levels. We are especially interested in candidates who bring scientific insight into wind energy, applied statistical meteorology, climate data, or geo-spatial analysis — with the curiosity and motivation to learn more about these fields.\n\nYou do not need to meet every qualification to apply. If you’re excited about the role and believe you could contribute, we encourage you to submit an application.\n\nYou might be a good fit if you have experience with one or more of the following:\n\n\nA background in wind energy, atmospheric science, Earth system science, or a related technical field (e.g., geophysics, applied physics, mechanical engineering, or environmental modelling)\nExperience working with scientific or geospatial data\nInterest in understanding and working with scientific models written in Fortran\nProgramming in Python, especially using tools like xarray, numpy, or pandas\nFamiliarity with tools like Git, Linux, and Docker\nExposure to GIS, remote sensing, or scientific workflow automation\n\n\nWe’re especially interested in candidates who are:\n\n\nCurious and eager to learn\nAble to collaborate with researchers and domain experts\nMotivated to make scientific software more usable, reproducible, and impactful\n\n\nWhat We Offer In Return\n\nAt DTU, you will help shape the scientific foundations of the renewable energy transition. You’ll contribute to open-source libraries, public datasets, and research software used globally. You’ll work in a supportive, interdisciplinary environment with time and space to grow your technical skills.\n\nAs a software developer at DTU Wind, you will find\n\n\nA meaningful role working at the intersection of science and software\nCollaboration with leading researchers in wind energy\nFlexible working conditions and strong support for professional development\nA well-established team with open knowledge-sharing culture\nA chance to work on visible, high-impact tools like the Global Wind Atlas\n\n\nSalary and appointment terms\n\nAppointment will be based on the collective agreement with the Danish Confederation of Professional Associations (AC) or in accordance with the OAO-S Joint Agreement and the organization agreement for IT employees (Prosa).\n\nThis is a full-time position located at DTU’s Risø Campus in Roskilde, Denmark. We offer flexibility to work from home up to two days per week.\n\nThe expected start date is 1 January 2026, or as soon as mutually agreed.\n\nApplication and contact\n\nPlease submit your online application no later than 15 October 2025 (23:59 Danish time). Open the “Apply now” link, fill out the form and attach your motivated application, CV and exam certificates.\n\nIf you would like additional information about the position, please contact Technical Lead for Wind Resource Assessment Applications, Neil Davis on +45 93 51 13 11 or neda at dtu dot dk.\n\nApplications received after the deadline will not be considered.\n\nAll interested candidates irrespective of age, gender, disability, race, religion or ethnic background are encouraged to apply. As DTU works with research in critical technology, which is subject to special rules for security and export control, open-source background checks may be conducted on qualified candidates for the position.\n\nDTU Wind and Energy Systems has led wind energy research, teaching, and commercial activities since the 1970s. With approximately 400 staff, it is the world’s largest public research institute dedicated to wind and energy systems transition. Internationally recognized for pioneering wind technology and smart energy systems, the department is structured into four divisions: Materials and Components, Wind Turbine Technology, Wind Energy Systems, and Power and Energy Systems. In close collaboration with industry and public authorities, DTU Wind and Energy Systems develops cutting-edge solutions for a sustainable energy future and trains the next generation of engineers.\n\nAbout the Section: The Resource Assessment and Meteorology section is approximately 28 people, with professors, researchers, PhDs, and software developers. We develop the WAsP model and the PyWAsP interface to the model, along with several other highly important software tools. We carry out research on the atmosphere, and how wind turbines interact with it from a fundamental level to using the latest modelling techniques.\n\nTechnology for people\n\nDTU develops technology for people. With our international elite research and study programmes, we are helping to create a better world and to solve the global challenges formulated in the UN’s 17 Sustainable Development Goals. Hans Christian Ørsted founded DTU in 1829 with a clear mission to develop and create value using science and engineering to benefit society. That mission lives on today. DTU has 13,500 students and 6,000 employees. We work in an international atmosphere and have an inclusive, evolving, and informal working environment. DTU has campuses in all parts of Denmark and in Greenland, and we collaborate with the best universities around the world.","brief_summary_of_job":null,"existing_skills_from_job":["Full-time","Software Development","Software","Research Skills","Meteorology","Git","Engineering","Geographic Information Systems (GIS)","HTML","Physics","Programming","Python"],"existing_skills_from_database":[]},
  "coding_categories": {"languages":["Bash","C","C#","C++","CSS","Clojure","Dart","Elixir","Go","Groovy","Haskell","HTML","Java","JavaScript","Julia","Kotlin","Lua","MATLAB","Objective-C","Perl","PHP","PowerShell","Python","R","Ruby","Rust","Sass","Scala","Swift","TypeScript"],"frameworks":[".NET","Angular","Apache Spark","ASP.NET","Backbone.js","Bootstrap","CodeIgniter","Django","Ember.js","Express","FastAPI","Flask","Flutter","Hadoop","Ionic","jQuery","Laravel","Livewire","Meteor","NestJS","Next.js","Node.js","Nuxt.js","Phoenix","PHPUnit","PyTorch","React","React Native","Ruby on Rails","Spring Boot","Svelte","Symfony","Tailwind CSS","TensorFlow","Vue.js","Xamarin","Alpine.js","Filament","WordPress"],"databases":["MySQL","PostgreSQL","Redis","MongoDB","DynamoDB","MariaDB","NoSQL","Oracle","BigQuery","Elasticsearch","SQL","SQL Server","SQLite","Cassandra","CouchDB","Neo4j","InfluxDB","CockroachDB"],"tools":["Git","GitHub","GitLab","Bitbucket","Docker","Kubernetes","CI\/CD","Jenkins","Kafka","RabbitMQ","Amazon SQS","AMQP","PubSub","REST API","RESTful APIs","GraphQL","AWS","Azure","GCP","Terraform","Ansible","Puppet","Chef","Vagrant","Vault","Consul","Prometheus","Grafana","ELK Stack","Splunk"],"skills":["English","Danish","Communication","Full-stack development","Back-end development","Front-end development","Cloud computing","DevOps","Microsoft Excel","PowerBI","Power Platform","Agile","Scrum","Problem-solving","Team collaboration","Physical presence","Remote work","Hybrid work"],"colors":{"languages":"blue","frameworks":"purple","databases":"orange","tools":"indigo"}},
  "skill_aliases": {"bash":"Bash","c":"C","c plus plus":"C++","C plus plus":"C++","c sharp":"C#","C sharp":"C#","c#":"C#","c++":"C++","clojure":"Clojure","cpp":"C++","dart":"Dart","elixir":"Elixir","go":"Go","golang":"Go","Golang":"Go","groovy":"Groovy","haskell":"Haskell","java":"Java","java script":"JavaScript","Java script":"JavaScript","javascript":"JavaScript","Javascript":"JavaScript","js":"JavaScript","JS":"JavaScript","es5":"JavaScript","ES5":"JavaScript","es6":"JavaScript","ES6":"JavaScript","julia":"Julia","kotlin":"Kotlin","lua":"Lua","matlab":"MATLAB","Matlab":"MATLAB","objective c":"Objective-C","Objective C":"Objective-C","objective-c":"Objective-C","objc":"Objective-C","ObjC":"Objective-C","obj-c":"Objective-C","Obj-C":"Objective-C","perl":"Perl","php":"PHP","Php":"PHP","powershell":"PowerShell","Power Shell":"PowerShell","python":"Python","py":"Python","Py":"Python","phyton":"Python","r":"R","ruby":"Ruby","rust":"Rust","scala":"Scala","swift":"Swift","typescript":"TypeScript","Typescript":"TypeScript","ts":"TypeScript","TS":"TypeScript","mysql":"MySQL","postgresql":"PostgreSQL","postgres":"PostgreSQL","mongodb":"MongoDB","mongo":"MongoDB","redis":"Redis","sqlite":"SQLite","oracle":"Oracle","mssql":"SQL Server","sql server":"SQL Server","dynamodb":"DynamoDB","dynamo db":"DynamoDB","mariadb":"MariaDB","maria db":"MariaDB","nosql":"NoSQL","no sql":"NoSQL","bigquery":"BigQuery","big query":"BigQuery","elasticsearch":"Elasticsearch","elastic search":"Elasticsearch","cassandra":"Cassandra","couchdb":"CouchDB","couch db":"CouchDB","neo4j":"Neo4j","neo 4j":"Neo4j","influxdb":"InfluxDB","influx db":"InfluxDB","cockroachdb":"CockroachDB","cockroach db":"CockroachDB","aws":"AWS","amazon web services":"AWS","azure":"Azure","microsoft azure":"Azure","gcp":"GCP","google cloud platform":"GCP","google cloud":"GCP",".Net":".NET","angular":"Angular","angular js":"Angular","Angular js":"Angular","angularjs":"Angular","AngularJS":"Angular","apache spark":"Apache Spark","asp net":".NET","ASP net":".NET","asp.net":"ASP.NET","ASP.NET":".NET","asp.net core":".NET","ASP.NET Core":".NET","backbone":"Backbone.js","BackboneJS":"Backbone.js","backbone js":"Backbone.js","backbonejs":"Backbone.js","bootstrap":"Bootstrap","Bootstrap framework":"Bootstrap","twitter bootstrap":"Bootstrap","Twitter Bootstrap":"Bootstrap","code igniter":"CodeIgniter","codeigniter":"CodeIgniter","django":"Django","ember":"Ember.js","ember js":"Ember.js","emberjs":"Ember.js","EmberJS":"Ember.js","express":"Express","express.js":"Express","Express.js":"Express","expressjs":"Express","ExpressJS":"Express","fast api":"FastAPI","Fast api":"FastAPI","fastapi":"FastAPI","flask":"Flask","flutter":"Flutter","hadoop":"Hadoop","Hadoop":"Hadoop","ionic":"Ionic","Ionic framework":"Ionic","ionic framework":"Ionic","jquery":"jQuery","JQuery":"jQuery","JQUERY":"jQuery","laravel":"Laravel","meteor":"Meteor","meteor js":"Meteor","meteorjs":"Meteor","MeteorJS":"Meteor","nestjs":"NestJS","nest js":"NestJS","Nest JS":"NestJS","Nestjs":"NestJS","next js":"Next.js","Next js":"Next.js","next.js":"Next.js","nextjs":"Next.js","NextJS":"Next.js","node":"Node.js","Node":"Node.js","node.js":"Node.js","nodejs":"Node.js","NodeJS":"Node.js","nuxt js":"Nuxt.js","Nuxt js":"Nuxt.js","nuxt.js":"Nuxt.js","nuxtjs":"Nuxt.js","NuxtJS":"Nuxt.js","phoenix":"Phoenix","Phoenix framework":"Phoenix","pytorch":"PyTorch","Pytorch":"PyTorch","torch":"PyTorch","Torch":"PyTorch","react":"React","react.js":"React","React.js":"React","reactjs":"React","ReactJS":"React","react native":"React Native","ReactNative":"React Native","reactnative":"React Native","rn":"React Native","RN":"React Native","rails":"Ruby on Rails","Rails":"Ruby on Rails","ror":"Ruby on Rails","ROR":"Ruby on Rails","ruby on rails":"Ruby on Rails","Ruby On Rails":"Ruby on Rails","spark":"Apache Spark","Spark":"Apache Spark","spring":"Spring Boot","Spring":"Spring Boot","spring boot":"Spring Boot","Spring Boot":"Spring Boot","spring framework":"Spring Boot","Spring Framework":"Spring Boot","SpringBoot":"Spring Boot","springboot":"Spring Boot","svelte":"Svelte","symfony":"Symfony","tailwind":"Tailwind CSS","Tailwind":"Tailwind CSS","tailwind css":"Tailwind CSS","Tailwind Css":"Tailwind CSS","tailwindcss":"Tailwind CSS","TailwindCSS":"Tailwind CSS","tensorflow":"TensorFlow","Tensorflow":"TensorFlow","tensor flow":"TensorFlow","Vue":"Vue.js","vue":"Vue.js","vue js":"Vue.js","vue.js":"Vue.js","vuejs":"Vue.js","VueJS":"Vue.js","xamarin":"Xamarin","Xamarin Forms":"Xamarin","Xamarin.forms":"Xamarin","livewire":"Livewire","phpunit":"PHPUnit","alpine":"Alpine.js","alpine js":"Alpine.js","alpinejs":"Alpine.js","filament":"Filament","docker":"Docker","kubernetes":"Kubernetes","k8s":"Kubernetes","github":"GitHub","gitlab":"GitLab","bitbucket":"Bitbucket","terraform":"Terraform","puppet":"Puppet","chef":"Chef","git":"Git","jenkins":"Jenkins","kafka":"Kafka","rabbitmq":"RabbitMQ","amazon sqs":"Amazon SQS","amqp":"AMQP","pubsub":"PubSub","rest api":"REST API","restful api":"RESTful APIs","restful apis":"RESTful APIs","graphql":"GraphQL","ansible":"Ansible","vagrant":"Vagrant","vault":"Vault","consul":"Consul","prometheus":"Prometheus","grafana":"Grafana","elk stack":"ELK Stack","splunk":"Splunk","scrum":"Scrum","agile":"Agile","kanban":"Kanban","devops":"DevOps","ci\/cd":"CI\/CD","tdd":"TDD","bdd":"BDD","linux":"Linux","windows":"Windows","macos":"macOS","ubuntu":"Ubuntu","centos":"CentOS","debian":"Debian","junit":"JUnit","pytest":"PyTest","jest":"Jest","mocha":"Mocha","cypress":"Cypress","selenium":"Selenium","html":"HTML","HTML":"HTML","html5":"HTML","HTML5":"HTML","css":"CSS","CSS":"CSS","css3":"CSS","CSS3":"CSS","sass":"Sass","scss":"Sass","SCSS":"Sass","less":"Less","LESS":"Less","webpack":"Webpack","gulp":"Gulp","npm":"npm","yarn":"Yarn","sql":"SQL","full time":"Fuldtid","full-time":"Fuldtid","fuldtid":"Fuldtid","part time":"Deltid","part-time":"Deltid","deltid":"Deltid","contract":"Kontrakt","kontrakt":"Kontrakt","remote":"Fjernarbejde","fjernarbejde":"Fjernarbejde","hybrid":"Hybridarbejde","hybridarbejde":"Hybridarbejde","on-site":"Fysisk tilstedeværelse","onsite":"Fysisk tilstedeværelse","fysisk tilstedeværelse":"Fysisk tilstedeværelse"}
}

## TASK:
1. **Extract ALL coding languages and frameworks** mentioned in the job description
2. **Use the skill_aliases mapping** to normalize skill names (e.g., "JS" → "JavaScript", "React.js" → "React")
3. **Only include skills from the coding_categories** (languages and frameworks)
4. **Avoid duplicates** - if "JavaScript" and "JS" are both mentioned, only include "JavaScript"
5. **Be thorough** - look for skills mentioned in:
   - Job title
   - Job description
   - Brief summary
   - Requirements sections
   - Nice-to-have sections

## SKILL CATEGORIES TO EXTRACT:
- **Languages**: Programming languages (PHP, Python, JavaScript, Java, C#, Go, Rust, etc.)
- **Frameworks**: Web frameworks and libraries (Laravel, React, Vue.js, Angular, Django, Spring Boot, etc.)
- **Databases**: Database systems and data stores (MySQL, PostgreSQL, Redis, MongoDB, DynamoDB, etc.)
- **Tools**: Development tools and infrastructure (Git, Docker, AWS, CI/CD, Jenkins, Kafka, etc.)

## EXCLUSION RULES:
- Do NOT extract general skills (communication, languages like English, etc.)
- Do NOT extract business skills (Excel, PowerBI for non-technical roles)
- Do NOT extract work arrangements (remote, physical presence)
- Do NOT include methodologies (Agile, Scrum, etc.) unless specifically technical
- Do NOT include skills already in existing_skills_from_database

## OUTPUT FORMAT:
Return ONLY valid JSON in this exact structure:
{
  "job_id": <integer>,
  "extracted_skills": [
    {
      "skill_name": "<normalized_skill_name>",
      "category": "<languages|frameworks|databases|tools>",
      "confidence": <integer 0-100>,
      "mentioned_as": ["<original_mention_1>", "<original_mention_2>"],
      "context": "<brief_context_where_found>"
    }
  ],
  "reasoning": {
    "total_skills_found": <integer>,
    "skills_by_category": {
      "languages": ["<skill1>", "<skill2>"],
      "frameworks": ["<skill1>", "<skill2>"],
      "databases": ["<skill1>", "<skill2>"],
      "tools": ["<skill1>", "<skill2>"]
    },
    "duplicates_removed": ["<original_mention> → <normalized_name>"],
    "excluded_skills": ["<skill>", "<reason>"]
  },
  "confidence": <integer 0-100>
}

Return nothing outside the JSON object.

{
  "job_id": 4419,
  "extracted_skills": [
    {
      "skill_name": "Fortran",
      "category": "languages",
      "confidence": 90,
      "mentioned_as": ["Fortran"],
      "context": "Integrating new scientific methods into our Fortran and Python-based tools"
    },
    {
      "skill_name": "Python",
      "category": "languages",
      "confidence": 100,
      "mentioned_as": ["Python"],
      "context": "Integrating new scientific methods into our Fortran and Python-based tools"
    },
    {
      "skill_name": "Git",
      "category": "tools",
      "confidence": 100,
      "mentioned_as": ["Git"],
      "context": "Familiarity with tools like Git, Linux, and Docker"
    },
    {
      "skill_name": "Linux",
      "category": "tools",
      "confidence": 80,
      "mentioned_as": ["Linux"],
      "context": "Familiarity with tools like Git, Linux, and Docker"
    },
    {
      "skill_name": "Docker",
      "category": "tools",
      "confidence": 90,
      "mentioned_as": ["Docker"],
      "context": "Familiarity with tools like Git, Linux, and Docker"
    }
  ],
  "reasoning": {
    "total_skills_found": 5,
    "skills_by_category": {
      "languages": ["Fortran", "Python"],
      "frameworks": [],
      "databases": [],
      "tools": ["Git", "Linux", "Docker"]
    },
    "duplicates_removed": [],
    "excluded_skills": []
  },
  "confidence": 90
}