R Systems
Website:
rsystems.com
Job details:
5 to 8 years of overall IT experience, with a minimum of 3 years Generative AI engineering roles
Large Language Model,AutoGen,GPT-4,Claude,Gemini,RAGAS,prompting
Hands-on experience building and deploying production-grade applications using large language models such as GPT-4, Claude, Gemini
- Experience developing Retrieval-Augmented Generation (RAG) pipelines — covering document ingestion, chunking strategies, embedding generation, vector indexing, and query reranking
- Experience designing and implementing agentic workflows with tool use, function calling, memory management, and multi-step reasoning using LangChain, LangGraph, AutoGen, or CrewAI.
- Demonstrated experience with advanced prompt engineering techniques including few-shot learning, chain-of-thought prompting, structured output generation, and system prompt design for enterprise use cases
- Experience building LLM evaluation pipelines to measure accuracy, groundedness, faithfulness, and hallucination using frameworks such as RAGAS, TruLens, DeepEval, or LLM-as-judge patterns.
Experience with LLMOps practices including prompt versioning, model endpoint monitoring, cost tracking per request, and latency optimisation in production GenAI systems.
- Strong written and verbal communication skills with the ability to explain LLM concepts, trade-offs, and risks to non-technical stakeholders and business leaders.
Click on Apply to know more.