Max Healthcare - Generative AI Engineer - Python/LLM

<p><p>Location : Max Healthcare, Gurgaon Head Office.<br/><br/> Employment Type : Full-time.<br/><br/> Experience : 2 to 4 years.<br/><br/> <b>Role Overview :</b> <br/><br/> We are looking for an AI Engineer with strong expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AWS cloud infrastructure.<br/><br/> The candidate will architect, develop, and deploy AI agents and RAG pipelines, integrate vectorized knowledge bases, and build scalable applications leveraging Python, React, and containerized AWS services.<br/><br/> <b>Responsibilities :</b> <br/><br/> - Build and optimise RAG workflows with vector databases and embeddings.<br/><br/> - Fine-tune, prompt-engineer, and deploy LLMs (Bedrock, GPT, Llama, Claude, etc.) for domain-specific production workloads.<br/><br/> - Develop Python backend services (APIs, orchestration) and React UIs for AI-powered apps.<br/><br/> - Deploy and manage AI workloads on AWS (EKS/ECS, Aurora Postgres, OpenSearch pgvector, SQS, Lambda, Elastic Cache, Secrets Manager).<br/><br/> - Implement guardrails, monitoring, and evaluation for safe and reliable AI agents.<br/><br/> - Collaborate with product and infra teams to ensure scalability, performance, and compliance.<br/><br/> <b>Skills & Experience :</b> <br/><br/> - 2 to 4 years in AI/ML engineering with proven LLM + RAG project experience.<br/><br/> - Strong in Python (AI pipelines, APIs) and exposure to React.js.<br/><br/> - Hands-on with AWS AI & infra : EKS/ECS, Aurora PostgreSQL, OpenSearch/pgvector, SQS, Lambda, S3, Secrets Manager.<br/><br/> - Knowledge of databases : Postgres, MongoDB, Neo4j, Vector DB.<br/><br/> - Familiar with Lang-Chain, Llama-Index and Hugging Face.<br/><br/> - Good understanding of containerization (Docker/Kubernetes) and CI/CD (CDK/Code-Pipeline).<br/><br/> - Knowledge of async processing, DLQ handling, and scalable message-driven architectures.<br/><br/> <b>Must to Have :</b> <br/><br/> - Experience with Amazon Bedrock and building LLM-based agents.<br/><br/> - ML-Ops exposure (ML flow, W&B).<br/><br/> - Graph/RAG hybrid architectures (Neo4j + vector DB).<br/><br/> - Experience with prompt guardrails, structured output validators, and secure data handling.<br/><br/></p><br/></p> (ref:hirist.tech)