AI Engineer - RAG Applications (5-8 yrs)

Job Description :

Experience : 6 years & Plus

Location : Pune, Mumbai, Bangalore, Gurgaon

Requirements : Immediate joiners with good comms, work from office required, and shift timing from 5 PM to 2 am IST.

Job Title : AI Engineer

Required Skills :

- Strong hands-on experience building AI/LLM-based RAG applications and AI agents.

- Experience with LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, or similar agent frameworks.

- Experience with MCP servers and MCP client integrations.

- Proficiency in Python and backend/API development.

- Experience building services with FastAPI.

- Strong understanding of LLMs, AI agents, RAG, embeddings, rerankers, vector databases, and retrieval systems.

- Experience with prompt engineering, tool calling, structured outputs, and agent orchestration.

- Experience with foundation models such as GPT, Claude, Llama, Gemini, Amazon Nova, or equivalent.

- Experience with vector databases such as Pinecone, ChromaDB, Qdrant, Weaviate, or similar technologies.

- Experience with object/blob storage such as Amazon S3.

- Experience with search and vector search systems such as Amazon OpenSearch.

- Experience with semantic search, hybrid search, BM25, and retrieval optimization techniques.

- Experience with cross-encoders, bi-encoders, reranking models, and embedding models.

- Experience with AI observability and evaluation tools.

- Experience with Git commands.

- Experience using GitHub and GitHub Actions for version control, CI/CD, and collaboration.

- Experience with SQL and database design.

- Knowledge of cloud security, authentication, authorization, and secure AI application development.

Responsibilities :

- Build AI/LLM applications on AWS using AWS services.

- Prompt engineering and evaluation frameworks.

- Build AI agents using frameworks such as LangChain, LangGraph, Amazon Bedrock, AutoGen, or similar tools.

- Develop backend services and APIs using FastAPI.

- Integrate AWS services such as Amazon Bedrock, S3, Lambda, ECS/EKS, OpenSearch, and AWS database services.

- Work with foundation models such as OpenAI GPT, Anthropic Claude, Meta Llama, Amazon Nova, Gemini, or similar models.

- Design and implement AI agent architectures, multi-agent systems, and tool-calling workflows.

- Implement RAG pipelines using blob/object storage, vector search, embeddings, reranking, and document retrieval workflows.

- Build semantic search, hybrid search, and knowledge retrieval systems.

- Implement prompt engineering, prompt management, and LLM evaluation strategies.

- Develop structured output and function/tool-calling capabilities.

- Implement streaming AI responses using SSE or WebSockets.

- Implement AI application monitoring, observability, tracing, and evaluation frameworks.

- Design guardrails, content filtering, hallucination mitigation, and responsible AI controls.

- Optimize AI applications for latency, scalability, reliability, and cost.

- Work with application teams to move AI prototypes into reliable production environments.

- Implement cloud security best practices.

- Collaborate with DevOps and platform teams to deploy, monitor, and scale AI workloads.

Nice to Have :

- Experience with Node.js and TypeScript.

- Experience with Amazon Bedrock, SageMaker, Azure OpenAI, OpenAI APIs, Anthropic APIs, or Google Vertex AI.

- Experience containerizing and deploying applications using Docker and Kubernetes.

- Experience with AI observability platforms such as Langfuse, Arize Phoenix, Helicone, or similar tools.

- Experience with model evaluation frameworks such as Ragas, DeepEval, LangSmith, or similar tools.

- Experience building multi-agent systems and autonomous workflows.

- Knowledge of enterprise security, compliance, governance, and cost optimization practices.

- Experience deploying production-grade AI solutions on AWS.

- Familiarity with MLOps, LLMOps, CI/CD, and Infrastructure as Code (Terraform, CloudFormation).