20 Aug
|
Sama
|
Coimbatore
Experience: 4+ yrs
Must-Have Skills
✔ vLLM / TensorRT-LLM / Triton Inference Server
✔ CUDA, cuDNN, NCCL
✔ GPU Performance Engineering & Multi-GPU Architecture
✔ Model Quantization (INT8, FP16, GPTQ, AWQ)
✔ AWS GPU Instances & AWS Inferentia
✔ Performance Profiling (Nsight, DCGM, nvidia-smi)
✔Kubernetes, KServe, Docker (preferred)
Tech Stack
vLLM | NVIDIA Triton | TensorRT-LLM | CUDA | AWS Inferentia | Neuron SDK | KServe | Prometheus | Locust | Kubernetes | Docker
Pay: ₹238,809.77 - ₹804,206.66 per year
Experience:
- GPU: 3 years (Required)
Work Location: In person
📌 GPU/ML Systems Engineer (Coimbatore)
🏢 Sama
📍 Coimbatore