Get AI-powered advice on this job and more exclusive features.
Location: Chennai / Pune / Bangalore / Noida / Gurgaon - 3 days hybrid
Experience: 5+ Years
Role Overview:
We're looking for a Senior LLM Engineer with strong hands-on experience in Python and Generative AI / LLM solutions, including Langchain and RAG (Retrieval-Augmented Generation) pipelines. This role is ideal for someone who has transitioned from a Software or ML Engineering background into the LLM/GenAI space over the last 3–4 years and is looking to contribute to building cutting-edge AI systems.
Key Responsibilities:
- Design and develop LLM-powered systems using Langchain, RAG, and agent-based frameworks.
- Build intelligent, context-aware solutions using prompt engineering, embedding models, and vector databases.
- Collaborate on the technical roadmap and architecture for LLM solutions.
- Translate real-world business use cases into scalable, production-ready AI systems.
- Work closely with business SMEs and data teams to align AI development with operational goals.
- Lead or participate in code reviews, performance tuning, and best practices adoption.
Core Skill Set:
- Python (Expert-level)
- RAG Pipelines & Prompt Engineering
- LLM Internals: embeddings, tuning, agent workflows
- SQL for data handling and queries
- System-level design and AI pipeline integration
- Excellent communication and cross-functional collaboration
Preferred Qualifications:
- 1+ years in LLMs/GenAI project development
- Familiar with MLOps and scalable AI architecture
- Prior exposure to client-facing roles or AI product delivery teams
Seniority level
Employment type
Job function
- Engineering, Consulting, and Information Technology
Industries
- IT System Testing and Evaluation, Software Development, and Technology, Information and Media