AI Architect

AI Architect – GenAI / RAG / Knowledge Graph

Experience: 9–12 Years

Work Type: Contractual

Role Overview

We are looking for an experienced AI Architect to own the end-to-end technical architecture of an enterprise AI platform. The role will focus on designing scalable GenAI, LLM, RAG, Knowledge Graph, NLP and Semantic Layer solutions that enable users to interact with enterprise cost, utilization, monitoring and compliance data through natural language.

The ideal candidate should have strong experience in AI/ML architecture, GenAI, LLMs, RAG, knowledge graphs, cloud platforms, MLOps/LLMOps and enterprise architecture , along with proven experience leading end-to-end AI/ML implementations.

Key Responsibilities

AI & GenAI Architecture

• Design end-to-end architectures for GenAI, LLM, RAG and agentic AI solutions .
• Define architecture for LLM orchestration, vector databases, retrieval pipelines and AI services.
• Design solutions using frameworks such as LangChain, LlamaIndex, LangGraph, AutoGen, CrewAI or Semantic Kernel .
• Evaluate and select appropriate LLM providers, foundation models and AI technologies.
• Define strategies for model selection, prompt engineering, retrieval, grounding and guardrails.

RAG & Retrieval Architecture

• Design production-grade RAG architectures involving:
• Embeddings
• Chunking
• Vector search
• Hybrid search
• Re-ranking
• Knowledge retrieval
• Citation/source attribution
• Define architecture for vector databases such as Pinecone, Weaviate, Milvus, pgvector or OpenSearch .
• Design hybrid retrieval combining vector search, semantic metrics and knowledge-graph queries.

Knowledge Graph & Ontology

• Design enterprise ontology and knowledge graph architecture .
• Define relationships between applications, services, infrastructure resources, accounts, subscriptions, cost centres, owners, SLAs, policies and compliance controls.
• Experience with Neo4j, Amazon Neptune, Stardog, GraphDB or equivalent .
• Strong understanding of RDF, OWL, SPARQL and/or Cypher .

Semantic Layer & Data Architecture

• Design semantic-layer architecture and enterprise data models.
• Align business metrics with FinOps Framework and FOCUS concepts.
• Define approaches for text-to-SQL, text-to-metric and text-to-graph-query.
• Ensure data quality, lineage, entity resolution and consistency across data sources.

Cloud & Platform Architecture

• Design cloud-native AI platforms on AWS and/or GCP .
• Experience with AWS Bedrock, Google Vertex AI or open-source foundation models .
• Design scalable microservices and API architectures.
• Strong understanding of Docker, Kubernetes, event-driven architecture and distributed systems .

MLOps / GenAIOps

• Define enterprise standards for:
• Model lifecycle management
• Prompt/version management
• Model evaluation
• LLM observability
• CI/CD
• Monitoring
• Cost/token optimization
• Establish quality gates around accuracy, groundedness, latency and cost per query .
• Experience with tools such as LangSmith, Langfuse, Ragas, DeepEval, Arize Phoenix or equivalent is desirable.

Security & Responsible AI

• Design AI solutions with security, privacy and compliance by design .
• Define RBAC and data-access controls.
• Establish guardrails against hallucination and unauthorized data access.
• Ensure enterprise requirements around auditability, data residency, PII and source attribution.

Leadership & Stakeholder Management

• Lead AI engineering teams and architecture/design reviews.
• Translate business requirements into technical architecture and implementation roadmaps.
• Collaborate with Cloud, Infrastructure, Security, Finance, Data Engineering, UI and DevOps teams .
• Own architecture decisions, technical risks and architecture decision records.
• Mentor senior engineers and guide technical implementation.

Mandatory Skills

• 9–12 years of total software/data/platform/AI engineering experience.
• 3–5+ years of hands-on experience in AI/ML/GenAI architecture or production implementation .
• Proven delivery of 2–3+ complete AI/ML project lifecycles .
• Strong Python .
• Strong GenAI / LLM / RAG architecture experience.
• Hands-on knowledge of AWS Bedrock / Vertex AI / Open-source LLMs .
• Experience with LangChain / LlamaIndex / LangGraph / AutoGen / CrewAI / Semantic Kernel …