Source description
About the role
Senior AI Engineer / GenAI Engineer AI / GenAI Department Experience: 35 years Positions: 3 Department: Artificial Intelligence (GenAI) Engagement: Full-time Role SummarySenior builder who designs RAG and agentic systems, owns quality and evaluation, and mentors junior engineers. Brings depth in advanced retrieval, multi-agent orchestration, and the operational side of running LLMs. Must-Have Skills Agentic frameworks LangGraph, CrewAI, or AutoGen; designing multi-step, multi-tool agents Advanced RAG hybrid search, re-ranking, query rewriting, GraphRAG Evaluation RAGAS, LangSmith, or custom evaluation pipelines Fine-tuning LoRA / PEFT, at least conceptual plus some hands-on LLMOps basics observability, cost/latency optimisation, guardrails Cloud AI platforms AWS Bedrock, Azure OpenAI, or GCP Vertex AI Good-to-Have Skills Model serving vLLM, quantization, open-weight models (Llama, Mistral, Qwen) Delivery CI/CD and MLOps tooling Key Responsibilities Own RAG and agent architecture for assigned features Design multi-agent and tool-using workflows Set up evaluation suites and quality gates Mentor junior engineers and review their work Drive performance, reliability, and cost improvements Location On-site : Mumbai, share your resume at hr@mintingminds.com Senior AI Engineer / GenAI Engineer AI / GenAI Department Experience: 35 years Positions: 3 Department: Artificial Intelligence (GenAI) Engagement: Full-time Role SummarySenior builder who designs RAG and agentic systems, owns quality and evaluation, and mentors junior engineers. Brings depth in advanced retrieval, multi-agent orchestration, and the operational side of running LLMs. Must-Have Skills Agentic frameworks LangGraph, CrewAI, or AutoGen; designing multi-step, multi-tool agents Advanced RAG hybrid search, re-ranking, query rewriting, GraphRAG Evaluation RAGAS, LangSmith, or custom evaluation pipelines Fine-tuning LoRA / PEFT, at least conceptual plus some hands-on LLMOps basics observability, cost/latency optimisation, guardrails Cloud AI platforms AWS Bedrock, Azure OpenAI, or GCP Vertex AI Good-to-Have Skills Model serving vLLM, quantization, open-weight models (Llama, Mistral, Qwen) Delivery CI/CD and MLOps tooling Key Responsibilities Own RAG and agent architecture for assigned features Design multi-agent and tool-using workflows Set up evaluation suites and quality gates Mentor junior engineers and review their work Drive performance, reliability, and cost improvements Location On-site : Mumbai, share your resume at hr@mintingminds.com
More at Minting Minds