Hyderabad, Telangana, India
• Staff AI engineer with strong experience in designing and building end-to-end RAG pipelines, including data ingestion, chunking, embeddings, retrieval optimization, reranking, grounding, and response validation. • Deep expertise in agent orchestration and multi-agent system design, using planner–worker patterns for task decomposition, coordination, and execution control. • Hands-on experience building agentic workflows using the OpenAI Agents SDK, with structured tool integration and orchestration via Model Context Protocol (MCP). • Strong background in LLM guardrails and reliability, including input sanitization, output validation, grounding checks, policy enforcement, and fallback mechanisms. • Proven experience implementing LLM evaluation frameworks, leveraging LLM-as-a-Judge techniques for relevance, factuality, and quality assessment. • Solid experience in GenAI data engineering, covering data collection, cleaning, transformation, labeling, versioning, and evaluation readiness. • Hands-on experience with LLM fine-tuning using Supervised Fine-Tuning (SFT) for domain-specific adaptation and task specialization. • Strong knowledge of Parameter-Efficient Fine-Tuning (PEFT) techniques for cost-effective and scalable model adaptation. • Strong focus on inference optimization, balancing latency, context window usage, throughput, and model selection trade-offs. • Extensive LLMOps and production deployment experience on AWS.