Key Responsibilities: Build enterprise-grade LLM applications using techniques such as RAG, tool calling, structured generation, prompt engineering, and agentic workflows. Implement and optimize LLM inference, including model serving, quantization, caching, batching, and GPU utilization where relevant. Develop LLM evaluation frameworks covering accuracy, relevance, hallucination, safety, latency, and cost. Work with open-source and commercial foundation models and assess their suitability for specific use cases. Build reusable components for enterprise AI applications, including knowledge retrieval, model gateways, evaluation pipelines, and agent orchestration.