Search 100,000+ live jobs across India

Free to search · AI fit score against your CV · tailor your résumé in one click

Job description

Core Responsibilities: • Develop, maintain, and scale a RAG-based chatbot system. • Build and optimize document ingestion pipelines, including parsing, chunking, embedding, and indexing large-scale text corpora. • Orchestrate LLM workflows using tools like custom logic for context construction, prompt templating, and fallback handling. • Own the end-to-end deployment stack: API development with FastAPI, and service management on cloud VMs. • Collaborate cross-functionally to identify automation opportunities, define solution scope, and incorporate user feedback into iterative model improvement. • Contribute to internal tooling for document updates, re-indexing, and evaluation, maintaining reliability across multiple knowledge domains. Experience: • Industrial experience of 7-10 years • 4+years of experience in building and deploying LLM-based system Skills & Competencies: Must Have: • A Bachelors degree (or above) in any relevant field (e.g., Computer Science, Statistics) is strongly preferred. • 4+ years of hands-on experience in AI/ML engineering, with real-world deployment of models and pipelines. • Strong expertise in Python • Proven experience building and deploying LLM-based systems, particularly those using retrieval-augmented generation (RAG). • Solid understanding of vector databases, embeddings, and semantic search architecture. • Strong skills in data engineering: ETL pipelines, data cleaning, transformation, and large-scale processing. • Experience in building REST APIs, containerizing services with Docker, and deploying to cloud infrastructure (preferably Azure or AWS). • Strong understanding of cloud platforms and modern data architectures (e.g., AWS, GCP, Azure).

More jobs at Tata Elxsi

All Tata Elxsi jobs (249)

Data jobs in Bengaluru

Data jobs in Bengaluru (3,439)

Other Data jobs in India

All Data jobs in India (11,207)