Job Summary

We are looking for an AI/Backend Engineer with strong expertise in Python, FastAPI, LLM integrations, and Retrieval-Augmented Generation (RAG) to build AI-powered enterprise applications. The role involves developing scalable backend services, document intelligence solutions, and retrieval systems using modern AI technologies.

Key Responsibilities

- Develop AI-powered backend services using Python and FastAPI.

- Integrate and manage LLMs such as OpenAI, Anthropic, and Google Gemini.

- Design and implement RAG pipelines for enterprise knowledge retrieval.

- Build document ingestion, parsing, chunking, embedding, indexing, and retrieval workflows.

- Integrate vector databases such as Qdrant, ChromaDB, or pgvector.

- Develop document intelligence capabilities including extraction, classification, summarization, and validation.

- Implement structured outputs, schema validation, and business-rule enforcement.

- Optimize AI services through caching, batching, rate limiting, and model selection.

- Evaluate retrieval accuracy, response quality, and AI model performance.

- Develop automated testing, monitoring, logging, and error-handling mechanisms.

- Collaborate with AI and product teams to enhance AI solutions and agent performance.

Required Skills

- Strong programming experience in Python.

- Hands-on experience with FastAPI, Flask, or similar frameworks.





- Experience integrating LLM APIs into production applications.

- Strong understanding of RAG, embeddings, semantic search, and vector databases.

- Experience with PostgreSQL or other relational databases.

- Knowledge of Qdrant, ChromaDB, pgvector, or similar vector stores.

- Experience with JSON, schema validation, and data transformation.

- Understanding of asynchronous processing and API optimization.

- Experience in unit testing and integration testing.

- Familiarity with AI evaluation, hallucination mitigation, and data quality practices.

Valuable to Have

- OCR and document-processing experience.

- Knowledge of reranking models and hybrid search.

- Experience with Neo4j or graph databases.

- Familiarity with MCP integrations.

- Experience with Redis, background workers, and message queues.

- Understanding of secure RAG and prompt injection prevention.

- Experience with Docker and cloud platforms (Azure/AWS/GCP).

Preferred Experience

- 3-8 years of backend development experience.

- Hands-on experience building and deploying AI-powered applications in production environments.

Expected Deliverables

- Production-ready AI APIs and backend services.

- Scalable RAG and document retrieval pipelines.

- Reusable LLM integration components.

- Document intelligence and validation solutions.

- Automated AI evaluation and quality monitoring frameworks.

📌 AI Backend Engineer (Chennai)
🏢 thinkpalm-technologies-pvt-ltd
📍 Chennai