Coffeebeans.io - Senior Generative AI Engineer - Large Language Models

Senior GenAI / LLM Engineer :Experience : 6+ Years.Location : Bangalore.Work Mode : Hybrid.Employment Type : Full-time.About the Role :CoffeeBeans is looking for a Senior GenAI / LLM Engineer to build and optimize production-grade Generative AI applications.The ideal candidate will have strong hands-on experience across LLM application development, prompt optimization, evaluation, guardrails, and observability.What You'll Do :- Build and optimize LLM/GenAI applications for real-world business use cases.- Design and improve prompts for accuracy, consistency, and reliability.- Create LLM evaluations (evals) to measure response quality, relevance, groundedness, and performance.- Design and implement custom guardrails for domain-specific AI applications, beyond basic prompt instructions.- Debug and improve LLM applications using LangSmith, MLflow, or similar observability tools.- Build and optimize RAG pipelines, including retrieval and context strategies.- Work with LLM frameworks and APIs to develop scalable AI solutions.- Collaborate with engineering, product, and business teams to take AI solutions from POC to production.Must Have :- 6+ years of software/AI/ML engineering experience.- Strong Python development experience.- Hands-on experience building GenAI/LLM applications.- Strong experience with Prompt Engineering / Prompt Optimization.- Experience writing and implementing LLM evals.- Experience building custom AI/LLM guardrails.- Hands-on experience with LangSmith, MLflow, or similar tools for LLM debugging/observability.- Experience with RAG, embeddings, and vector databases.- Experience with frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent.- Experience working with LLMs such as OpenAI, Anthropic, Gemini, Azure OpenAI, or open-source models.Good to Have :- Experience with AI Agents / Agentic AI.- Knowledge of MCP (Model Context Protocol).- Experience with Docker, Kubernetes, and cloud platforms.- Understanding of LLM security concepts such as prompt injection and hallucination prevention.What We're Looking For :- Someone who has hands-on experience building, evaluating, debugging, and improving real-world LLM applications - not just experimenting with prompts or ChatGPT.- If you're excited about building reliable, production-ready GenAI solutions, we'd love to hear from you! (ref:hirist.tech)