AI Context Architect

About the Role
Role : AI Context Architect
Experience: 10+ Years
Relevant Experience : Atleast 3+ Years as AI Architect is mandatory
Location : Chennai / Bengaluru
Role Summary
The AI Context Architect designs enterprise knowledge and context architectures that enable AI agents, copilots and applications to access accurate, secure, relevant and trustworthy information. The role focuses on building enterprise semantic layers using ontologies, taxonomies, semantic models and Knowledge Graphs. It architects GraphRAG and hybrid graph-vector retrieval solutions across Neo4j, Amazon Neptune, vector databases, relational databases and NoSQL platforms. The architect establishes governance over metadata, lineage, entity resolution, access control and explainability, while exposing trusted enterprise context through secure APIs and Model Context Protocol (MCP) servers. The ideal candidate is a hands-on AI-native engineer-architect capable of delivering production-grade knowledge and retrieval solutions, defining reusable reference architectures and supporting enterprise AI initiatives.
Responsibilities
Key Responsibilities
A. Semantic & Knowledge Modeling
Design enterprise ontologies, taxonomies and semantic models.
Define business entities, relationships and rules using graph and relational modeling.
Establish semantic modeling standards, naming conventions and versioning practices.
Collaborate with domain experts to translate business knowledge into machine-readable models.
B. Knowledge Graphs, GraphRAG & Retrieval Architecture
Architect Knowledge Graph and GraphRAG solutions using Neo4j, Amazon Neptune and related technologies.
Design hybrid graph-vector retrieval across graph databases, vector stores, RDBMS and NoSQL.
Develop embedding, chunking, indexing, ranking and query-planning strategies.
Implement semantic retrieval, graph traversal and hybrid search.
Optimize retrieval accuracy, contextual relevance, latency and cost.
Design context assembly for enterprise AI agents and LLM applications.
C. Governance, Trust & Explainability
Establish metadata management, data lineage and provenance standards.
Implement entity resolution and master-data alignment across enterprise systems.
Design secure, policy-aware retrieval and granular access controls.
Enable traceable sources, citations and explainability in AI-generated responses.
Ensure enterprise AI solutions meet security, privacy and governance requirements.
D. MCP, APIs & Enterprise Integration
Design and develop secure MCP servers and context services.
Expose enterprise knowledge through REST/GraphQL APIs.
Integrate graph and retrieval platforms with enterprise data sources.
Implement scalable cloud-native microservices and event-driven architectures.
Connect context services with enterprise catalogs, identity systems and security platforms.
E. Evaluation, Observability & Optimization
Define evaluation frameworks for retrieval relevance, groundedness, completeness and accuracy.
Implement regression testing and retrieval quality metrics.
Establish monitoring, tracing and observability for context services.
Optimize query performance, indexing, caching and AI infrastructure costs.
Monitor retrieval quality, usage patterns and performance drift.
F. Engineering Practice & CoE Leadership
Build reusable Knowledge Graph, GraphRAG and context engineering accelerators.
Develop reference implementations, architecture patterns and technical playbooks.
Apply AI-native engineering and DevSecOps practices.
Mentor architects and engineers.
Support Solutions and Advisory teams during customer engagements.
Evaluate emerging graph, semantic and AI retrieval technologies.
Qualifications
Required Skills & Qualifications
Education & Experience
Bachelor's or Master's degree in Computer Science, Information Systems, Data Science or a related discipline, or equivalent practical experience.
10+ years in software, data or solution architecture.
At least 3 years in Knowledge Graphs, semantic modeling, search/retrieval or applied AI/LLM systems.
Experience delivering at least one graph-based or retrieval-based AI solution into production.
Required Skills
Technical Skills - Must Have
Knowledge Graph Architecture: Neo4j, Amazon Neptune, graph data modeling and enterprise knowledge representation.
Graph Query Languages: Cypher, Gremlin or SPARQL.
Semantic Architecture: Ontologies, taxonomies, semantic modeling and property graph design.
GraphRAG & Retrieval: GraphRAG, RAG, hybrid graph-vector retrieval, embeddings, vector databases and reranking.
Context Engineering: Context assembly, retrieval optimization, ranking, query planning and context-window management.
Enterprise Data Architecture: SQL, RDBMS, NoSQL and multi-source retrieval integration.
Data Governance: Metadata management, data lineage, entity resolution, provenance and access controls.
MCP & APIs: MCP server development, REST/GraphQL APIs and enterprise integration.
AI-Native Engineering: Hands-on experience with Claude Code, GitHub Copilot, Codex, Kiro or Cursor.
Programming: Python, TypeScript/Node.js or Java.
Cloud-Native Architecture: AWS, Azure or GCP, microservices, containers and event-driven architecture.
DevSecOps: CI/CD, infrastructure as code, secrets management and secure SDLC.
AI Evaluation: RAG evaluation, retrieval quality, groundedness, observability and cost optimization.
Behavioral & Professional Skills
Strong analytical and architecture design capabilities.
Ability to translate complex business concepts into semantic models.
Effective communication with business stakeholders and engineering teams.
Strong technical documentation and consulting skills.
Mentoring, collaboration and

Work arrangement
Hybrid