Senior AI Engineer, Knowledge Graph & GenAI

Coditude; Pune District; On-site; INR 6,000,000 - 10,000,000; Full time

Job summary

Coditude is seeking a hands-on Senior AI Engineer to build production-grade AI systems using Generative AI, RAG, GraphRAG, knowledge graphs and vector search. You will deploy end-to-end pipelines across healthcare, enterprise software and data platforms, taking solutions from experimental to production-ready.

The ideal candidate has strong software engineering fundamentals, extensive hands-on experience with LLMs and RAG systems, and the ability to work across AI, backend, data and cloud

Qualifications

• 5+ years of software engineering with hands-on AI/ML or GenAI.
• Strong Python skills and FastAPI experience.
• Hands-on with RAG, LLM and AI agent applications.
• Experience with LangChain, LangGraph, LlamaIndex or equivalents.
• Strong understanding of embeddings, vector search and semantic retrieval.
• Experience with Qdrant, Pinecone, ChromaDB, pgvector or similar.
• Neo4j and Cypher experience is highly desirable.
• Strong PostgreSQL/SQL and Redis skills.
• Experience with Node.js / TypeScript; Next.js/React a plus.
• Experience with AWS and/or GCP, Docker and CI/CD.
• Strong API design, asynchronous processing, testing and debugging.
• Good communication and ability to own problems independently.

Responsibilities

• Build production-grade RAG and GraphRAG systems with LLMs, vector search, knowledge graphs and data.
• Develop LLM workflows using LangChain, LangGraph, LlamaIndex or equivalents.
• Build AI agents, tool-calling workflows and stateful AI pipelines.
• Implement embeddings, semantic search, chunking, reranking and hybrid retrieval.
• Develop text-to-SQL, text-to-Cypher and NL query systems.
• Build LLM evaluation pipelines to optimize accuracy, latency and cost.
• Work with LLM APIs and batch processing using OpenAI, Anthropic and other models.
• Design and work with Neo4j knowledge graphs, graph modelling and Cypher queries.
• Build semantic enrichment pipelines including entity extraction and linking.
• Develop data pipelines with Apache Airflow or equivalent orchestration tools.
• Work with PostgreSQL, Redis, Qdrant and other vector databases.
• Process and index large-scale enterprise datasets for AI apps.
• Architect multi-tenant SaaS platforms with strong data isolation.
• Build and maintain data pipelines with Apache Airflow, ETL, DAG orchestration and data quality checks.
• Design scalable APIs/services in Python (FastAPI) and Node.js/TypeScript.
• Deploy and operate workloads on AWS and GCP using serverless, containerised patterns.

Skills

Python

FastAPI

RAG systems

LangChain

LangGraph

LlamaIndex

embeddings

vector search

Neo4j

PostgreSQL

Redis

Node.js/TypeScript

AWS/GCP

Docker

Education

Bachelor’s degree in Engineering (IT / Computer Science)

Tools

Qdrant

Pinecone

ChromaDB

pgvector

Airflow

FastAPI

Job description

6-10years

Full-Time

ROLE OVERVIEW

We are looking for a hands-on Senior AI Engineer to build production-grade AI systems using Generative AI, RAG, GraphRAG , knowledge graphs, vector search, LLM orchestration and computer vision. You will work on real-world AI products across healthcare, enterprise software and data platforms, taking solutions from experimentation to production.

The ideal candidate has strong software engineering fundamentals, hands-on experience with LLMs and RAG systems, and the ability to work across AI, backend, data and cloud technologies.

KEY RESPONSIBILITIES

• Build production-grade RAG and GraphRAG systems combining LLMs, vector search, knowledge graphs and structured data.
• Develop LLM workflows using LangChain, LangGraph, LlamaIndex or equivalent frameworks.
• Build AI agents, tool-calling workflows and stateful AI pipelines.
• Implement embeddings, semantic search, chunking, reranking and hybrid retrieval.
• Develop text-to-SQL, text-to-Cypher and natural-language query systems.
• Build LLM evaluation pipelines and optimise accuracy, latency and cost.
• Work with LLM APIs and batch processing using models such as OpenAI, Anthropic and other foundation models.

Knowledge Graphs & Data

• Design and work with Neo4j knowledge graphs, including graph modelling and Cypher queries.
• Build semantic enrichment pipelines including entity extraction, entity linking and relationship extraction.
• Develop data pipelines using Apache Airflow or equivalent orchestration tools.
• Work with PostgreSQL, Redis, Qdrant and other vector databases.
• Process and index large-scale enterprise datasets for AI applications
• Architect multi-tenant SaaS platforms with strong data isolation across database, storage, API and orchestration layers.
• Build and maintain data pipelines with Apache Airflow, including ETL, DAG orchestration, data quality checks and real-time synchronisation.
• Design scalable APIs and services in Python (FastAPI) and Node.js / TypeScript, backed by PostgreSQL, Neo4j, Redis and vector stores.
• Deploy and operate workloads on AWS and GCP using serverless, containerised and event-driven patterns.

Security & Compliance

• Enforce HIPAA-grade controls: encryption with KMS, RBAC, JWT/OAuth authentication, audit logging and per-tenant key management.
• Translate regulatory and client compliance requirements into concrete architecture and engineering standards.

Leadership & Delivery (Nice to Have)

• Lead and mentor a team of 2 to 4 engineers through architecture reviews, code reviews, sprint planning and delivery milestones.
• Act as the primary technical point of contact for clients: gather requirements, propose solutions, report progress and manage expectations.
• Raise the bar on code quality, documentation, testing and engineering practices across the team.

REQUIRED SKILLS & EXPERIENCE

• 5+ years of software engineering experience with significant hands-on experience in AI/ML or GenAI.
• Strong Python skills and experience with FastAPI .
• Hands-on experience building RAG, LLM and AI agent applications .
• Experience with LangChain, LangGraph, LlamaIndex or equivalent.
• Strong understanding of embeddings, vector search and semantic retrieval .
• Experience with Qdrant, Pinecone, ChromaDB, pgvector or similar.
• Experience with Neo4j and Cypher is highly desirable.
• Strong PostgreSQL / SQL skills and experience with Redis.
• Experience with Node.js / TypeScript ; Next.js / React is a plus.
• Experience with AWS and/or GCP, Docker and CI/CD .
• Strong understanding of APIs, asynchronous processing, testing and debugging.
• Good communication skills and ability to independently own technical problems.

GOOD TO HAVE

• Experience with LLM or vision model fine-tuning workflows, GPU-backed training and model registries.
• Computer vision with PyTorch / TensorFlow, OpenCV, YOLO or U-Net.
• Payment and real-time integrations such as Stripe, Razorpay, Socket.io or Pusher.
• Comfort with AI-assisted development tools such as Cursor or Claude Code.

QUALIFICATIONS

• Bachelor’s degree in Engineering (IT / Computer Science) or equivalent practical experience.