AI/LLM Engineer - 5-10 yrs
Summary
Build and deploy production AI/LLM applications in Python — RAG pipelines, embeddings, vector search, AI agents, tool calling and multi-step workflows — plus backend REST services and LLM evaluation/grounding frameworks. On-site role in Lower Parel, Mumbai for engineers with 5+ years in AI/ML and 2+ years hands-on with LLMs.
Position Details:
- Position Name: AI/LLM Engineer
- Location: Lower Parel, Mumbai
- Work Mode: Work From Office Only
- Immediate joiners or candidates with 15 - 30 days of Notice Period are preferred
Responsibilities:
- 5+ years of overall experience in AI/ML Engineering, including a minimum of 2 years of hands-on experience with LLMs.
- Strong proficiency in Python for developing, deploying, and maintaining AI/LLM-based applications.
- Hands-on experience with LLMs, RAG (Retrieval-Augmented Generation), embeddings, and vector databases/search.
- Experience building multi-step LLM workflows, AI agents, tool calling, function calling, and orchestration.
- Strong understanding of prompt engineering, context retrieval, and grounded generation to ensure accurate, traceable outputs.
- Experience implementing structured outputs, schema validation, guardrails, and hallucination prevention techniques.
- Hands-on experience developing backend services, REST APIs, data integrations, and deploying AI solutions.
- Experience building LLM evaluation frameworks, regression testing, grounding checks, and debugging multi-step workflows.
- Knowledge of model fine-tuning, model adaptation, and experience in regulated domains such as BFSI, healthcare, or legal is an advantage.
- Strong analytical and problem-solving skills, with a focus on AI output accuracy, reliability, scalability, and production readiness.