Developer : Graph Engineer LLM & AI (m / f / n)

The aim of “Generate Insights from Hidden Knowledge (GIHK)” is to gather evidence and generate insights supporting strategic and tactical decisions in several key phases in the later stages of pharma value chain.

The goal is to create the Customer & Launch (CL) Knowledge Graph HUB (named “GIHK Data Factory”) that includes Knowledge Graphs and GraphRAGs for further use that leverage LLMs, ontologies, and semantic knowledge representation to improve knowledge discovery, question answering, and information retrieval.

Tasks:

• Independent development of codes and machine learning models depending on assigned user feedback.
• Independent development of features in the application/system in line with BI architecture, good coding practices and business priorities.
• Independent unit testing units of code quality to provide proper results based on use cases.
• Independent System Integration Testing & User Acceptance Testing to confirm and identify gaps.
• Resolving the resulting bugs and issues within the sprint framework and hand over to BI if unresolvable.
• Creation of Knowledge Graphs and GraphRAGs: The task involves designing, developing, and deploying Knowledge Graphs and GraphRAGs to structure and semantically integrate domain-specific knowledge, enhancing data interoperability.
• Graph Querying and Data Modeling: Performing basic and advanced graph querying, data modeling, and graph analytics on large production knowledge graphs.
• Development of Production Code: Supporting the ingress and egress of data from the knowledge graphs and GraphRAGs by developing production-ready Python code.
• Data Science and Visualization: Developing data science and visualization tools as needed to support the GIHK product team.
• AI and Machine Learning Integration: Utilizing AI, machine learning, and NLP technologies to enhance the knowledge graph and improve data retrieval and user interactions.
• Implementation of Workflows: Implementing workflows and methodologies for scalable validation of LLM-based models and systems.
• Consultation of data scientists, subject matter experts, and engineers to define, model, and implement ontologies that align with business requirements.
• Documentation: Documenting development processes, architecture, and APIs to ensure maintainability and knowledge sharing.
• Consultation for Graph Analytics: Supporting other projects related to graph analytics and visualization, and helping internal clients understand, explore, and access the graph environment.

Qualifications:

Bachelor’s or Master’s degree (Preferred) in Computer Science, Data Science, Artificial Intelligence, or a related field.

• 6-10+ years of professional experience in the related fields including Software Development Life Cycle (SDLC).
• 2-5 years of proven experience in developing AI applications with large language models (e.g., OpenAI, BERT, GPT-3 / 4) or natural language processing techniques.
• Strong background in knowledge representation and semantic technologies, including ontologies, RDF, OWL, and SPARQL.
• Proficiency in programming languages like Python and experience with machine learning frameworks (e.g., TensorFlow, PyTorch).
• Knowledge or experience with Semantic Web Technologies and linked data.
• Experience using Graph Data Science toolkit or an understanding of graph algorithms such as centrality, community detection, node embedding, link prediction, etc.
• Excellent analytical and problem-solving skills, with a keen attention to detail.
• Strong communication skills and the ability to work collaboratively in a cross-functional team environment.

Skills:

• Strong Knowledge in Pharma and Life Science.
• Strong experience with retrieval-augmented generation (RAG, GRAPHRAG; KAG) frameworks or applications.
• Strong experience with graph databases (e.g., Neo4j, AWS Neptune) and knowledge graph construction.
• Strong Knowledge on LLM Applications, NLP.
• Strong Knowledge on Ontologies and Knowledge Graphs.
• Familiarity with data integration, data cleaning, and linking methodologies.
• Knowledge of MLOps practices, cloud platforms (AWS, Azure, GCP), and deployment of AI models in production.
• Familiarity with knowledge base management, content indexing, and search optimization techniques.