Key Responsibilities

· Design enterprise taxonomies, ontologies, metadata frameworks and semantic models.

· Build and maintain knowledge graphs and semantic search architectures.

· Design and optimise RAG, Agentic RAG and GraphRAG solutions.

· Develop chunking, embedding, indexing, retrieval, reranking and grounding strategies.

· Implement vector databases and retrieval pipelines for structured and unstructured content.

· Build Python-based ingestion, enrichment and knowledge pipelines on cloud platforms.

· Define knowledge quality, governance, lineage, discoverability and lifecycle standards.

· Partner with domain experts to convert business knowledge into reusable AI-ready assets.

· Evaluate retrieval quality, answer groundedness and system performance using measurable criteria.

Required Skills

· Information architecture, data modelling, taxonomy design, ontology modelling and metadata strategy.

· Knowledge graphs, semantic modelling and semantic technologies such as RDF, OWL and SPARQL.

· RAG, Agentic RAG, GraphRAG, embeddings, vector databases and semantic search.

· Chunking strategies, retrieval optimisation, reranking and retrieval evaluation.

· Python programming, APIs,



data pipelines and cloud-native engineering.

· Working knowledge of LLMs, agentic AI patterns and AI evaluation approaches.

· Solid critical thinking, structured problem-solving and stakeholder collaboration.

Experience & Qualifications

· 7+ years in data engineering, knowledge engineering, information architecture, search, cloud engineering or a related field.

· 3+ years building AI, LLM, RAG, knowledge graph or enterprise search solutions.

· Bachelor's or Master's degree in Computer Science, Data Science, Information Systems or a related discipline, or equivalent practical experience.

Preferred Skills

· Azure AI Search, Azure OpenAI, Microsoft Fabric, Microsoft Graph or Copilot ecosystem experience.

· Experience with SharePoint, Microsoft 365, Confluence, ServiceNow or similar enterprise content platforms.

· Exposure to agent frameworks, graph databases, Responsible AI and knowledge governance.

Success Measures

· Higher retrieval relevance and grounded answer quality.

· Improved knowledge discoverability, reuse and traceability.

· Scalable knowledge patterns adopted across multiple AI use cases.

📌 AI Knowledge Engineer (Bengaluru)
🏢 Quess IT Staffing (Formerly known as Magna Infotech)
📍 Bengaluru