17 Nov
|
Oddsfitness
|
New Delhi
17 Nov
Oddsfitness
New Delhi
Full-Stack AI Engineer RAG & LLM Systems
Company: ODDS Longevity
Experience: 3–6 years
Location: Delhi NCR / Gurugram
Role: Full-Time
About the Role
We are looking for a strong Full-Stack AI Engineer who has hands-on experience designing, implementing and deploying Retrieval-Augmented Generation (RAG) systems.
The candidate must understand how modern AI applications work beyond simple LLM API integrations and be capable of independently developing AI-powered products from backend architecture to frontend experiences.
Prior implementation of at least one working RAG system is mandatory.
Key Responsibilities
- Design, build and optimize end-to-end RAG pipelines, including document ingestion, chunking, embeddings, vector indexing, retrieval, reranking and LLM response generation.
- Build AI agents and intelligent workflows using tools such as LangChain, LangGraph, MCP or equivalent frameworks.
- Develop scalable backend services using Python, FastAPI and REST APIs.
- Build full-stack applications using React.js, Next.js, TypeScript and Node.js.
- Integrate LLMs such as OpenAI, Claude or Gemini with internal applications, APIs and databases.
- Work with vector databases such as Qdrant, Pinecone, Weaviate, Chroma or pgvector.
- Implement evaluation frameworks, hallucination mitigation, grounded responses, monitoring and performance optimization.
- Deploy, maintain and improve AI applications in production environments.
Mandatory Requirements
- 3–6 years of relevant software development experience, with strong Python and JavaScript/TypeScript capabilities.
- At least one hands-on RAG implementation, preferably deployed in a real-world application.
- Strong understanding of embeddings, vector databases, semantic search, retrieval strategies and LLM architecture.
- Practical experience with LangChain, LlamaIndex, LangGraph or similar AI frameworks.
- Experience with Python/FastAPI and React.js/Next.js.
- Understanding of LLM evaluation, prompt engineering, context management, token usage and latency optimization.
- Ability to independently design, develop, deploy and troubleshoot AI-driven systems.
Good to Have
- Experience with Supabase, PostgreSQL and pgvector.
- Experience with multi-agent architecture, MCP and AI tool calling.
- Familiarity with AWS, Docker or Railway.
- Experience building AI applications using sensitive or access-controlled data.
- Experience with React Native or Expo.
- Familiarity with healthcare or other data-intensive applications.
Significant Screening Requirement Candidates must be able to explain a RAG system they personally implemented, including architecture, retrieval pipeline, vector database selection, evaluation methodology and deployment challenges.
Candidates whose AI experience is limited to prompt engineering, API wrappers or basic chatbot integrations will not qualify.
📌 Full-Stack AI Engineer RAG & LLM Systems (New Delhi)
🏢 Oddsfitness
📍 New Delhi