Job Summary We are looking for an AI/Backend Engineer to develop AI-powered backend services, Retrieval-Augmented Generation (RAG) pipelines, document intelligence capabilities, and LLM integrations for enterprise applications. The candidate should have solid Python and API development skills, experience working with structured and unstructured data, and practical knowledge of LLMs, embeddings, vector databases, and AI evaluation.

Key Responsibilities
Develop and maintain AI-powered backend services using Python and FastAPI or equivalent frameworks. Integrate LLMs from providers such as OpenAI, Anthropic, and Google. Design and implement RAG pipelines for retrieving information from enterprise documents and data sources. Develop document ingestion, parsing, chunking, embedding, indexing, retrieval, and reranking pipelines. Integrate vector databases such as Qdrant, ChromaDB, pgvector, or equivalent technologies. Build document intelligence capabilities for information extraction, classification, summarization, and validation. Implement structured output generation and validate LLM responses against predefined schemas and business rules. Develop reusable AI components and services that can be consumed by multiple agents. Integrate AI services with relational databases, REST APIs, document repositories, and enterprise applications. Optimize AI service performance and cost through caching, batching, rate limiting, and model selection. Evaluate model outputs, retrieval accuracy, response quality, and factual consistency. Develop automated tests and evaluation datasets for AI pipelines. Implement error handling, retries, logging, and monitoring.



Collaborate with the Agentic AI Engineer to improve agent execution quality and troubleshoot AI-related failures. Maintain technical documentation for AI services, retrieval pipelines, and model integrations. Required Technical Skills Strong proficiency in Python. Experience developing APIs using FastAPI, Flask, or equivalent frameworks. Hands-on experience integrating LLM APIs into applications. Understanding of embeddings, semantic search, and vector similarity. Practical knowledge of RAG architecture and retrieval strategies. Experience with PostgreSQL or other relational databases. Familiarity with vector databases such as Qdrant, ChromaDB, or pgvector. Experience with JSON, structured outputs, schema validation, and data transformation. Understanding of asynchronous processing, caching, and API performance optimization. Experience writing unit and integration tests. Understanding of AI output evaluation, hallucination risks, and data quality. Good-to-Have Skills OCR and document processing libraries. Experience processing PDFs, Office documents, scanned files, and multimodal inputs. Knowledge of reranking models and hybrid search. Experience with Neo4j or other graph databases. Familiarity with MCP and enterprise tool integrations. Experience with Redis, background workers, and message queues. Knowledge of prompt injection risks and secure RAG implementation. Experience deploying AI services using Docker and cloud platforms. Expected Deliverables Reusable LLM integration services. Production-ready RAG and document retrieval pipelines. Document extraction, classification, and validation components. AI evaluation datasets and automated quality checks. Secure and scalable AI APIs with appropriate logging and error handling.

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