Job Summary Objectives & Responsibilities - Assist in designing and building GPU-accelerated micro-services for vision, LLM, and RAG workloads - Support the full model lifecycle: data capture, training, evaluation, packaging, and CI/CD deployment (Docker, Kubernetes, NVIDIA NIM) - Learn inference optimization with TensorRT, ONNX-Runtime, quantization, batching, and Triton - Help develop agent orchestration logic (LangChain, CrewAI) that chains tools, prompts, and APIs - Contribute to building a…