About the Role
We are looking for a hands-on AI Engineer to join our growing technology team and lead the
development of our Agentic RAG (Retrieval-Augmented Generation) system. This is a greenfield AI
project building an intelligent knowledge assistant for healthcare credentialing workflows, with a clear
roadmap from knowledge Q&A; (Phase 1) through to fully automated agentic actions (Phase 5). You will
work directly under the AI Project Lead and collaborate closely with our existing MERN stack
development team.
Key Responsibilities

- Design, develop, and maintain Retrieval-Augmented Generation (RAG) systems including

embedding pipelines, vector indexing, and retrieval optimization using Lang Chain and Long
Graph.

- Build and maintain the knowledge ingestion pipeline , URL scraping, PDF/DOCX processing,

chunking, embedding generation, and vector database indexing.

- Integrate and optimize Large Language Models via AWS Bedrock, including model selection,

prompt engineering, and cost/latency optimization.

- Implement agentic workflows using Lang Graph for multi-step reasoning, tool orchestration, and

autonomous task handling (Phase 2 onwards).

- Build and expose REST APIs using Quick API or Flask to connect the AI backend with the React-

based admin panel and chat widget.

- Implement AI monitoring frameworks including logging, hallucination detection, response

quality evaluation,



and performance tracking.

- Collaborate with the MERN stack team on frontend chat widget integration and knowledge

management portal UI.

- Maintain clean, well-documented, production-grade code with containerized deployments using

Docker on AWS.
Required Skills

- Python , strong, non-negotiable. This is the primary development language.
- Lang Chain and/or Lang Graph , hands-on experience building RAG or agentic pipelines.
- AWS experience , specifically Bedrock, S3, EC2. Familiarity with IAM and VPC is a plus.
- Vector databases , practical experience with at least one: pgvector, Pinecone, or Weaviate.
- REST API development , Fast API or Flask for building AI backend services.
- Docker and containerization , building and deploying containerized applications.
- SQL databases , comfortable writing queries and working with relational data.
- Understanding of embeddings, semantic search, and chunking strategies for RAG.

Good to Have

- React or basic JavaScript knowledge , for minor frontend coordination with the MERN team.
- Experience with Terraform or infrastructure-as-code tools.
- Familiarity with AI governance, hallucination detection, or response evaluation frameworks.
- Prior exposure to healthcare or compliance-heavy domains.
- Personal or open-source RAG/LLM projects on GitHub , highly valued over certifications.

📌 AI Engineer - Pune (2+ Years) (India)
🏢 Informica Solutions
📍 India