AI and Machine Learning Engineer

2+ years in MLOps, DevOps, or backend engineering for AI workloads

Expertise with DeepStream 7.x (pipelines, Gstplugins, nvdsanalytics, nvstreammux)

Strong experience with Docker & GPU scheduling

Proficiency optimizing inference on NVIDIA GPUs (TensorRT, CUDA toolkit, mixed precision)

Hands-on production deployment experience with YOLO (or similar CNNs)

Self-hosting & serving LLMs (vLLM, TensorRT-LLM, quantization, pruning, distillation)

Strong Python and Bash scripting skills; experience with CI/CD scripting