JOBSEARCHER

Cortex Engineer

AmpstekConcord, NCL5 SeniorOctober 31st, 2026
Job Title: Cortex Engineer
Location: Concord, CAJD :Inference engines / LLM servingvLLM, TGI (Text Generation Inference), TensorRT-LLM, Triton Inference Server, SGLang, Ray Serve, NVIDIA NIM, Ollama (dev only), llama.cpp, DeepSpeed-InferenceLLM performance optimization"continuous batching", "KV cache", "Paged Attention", "speculative decoding", "prefix caching", "tensor parallelism", "time to first token (TTFT)", "tokens per second", "throughput vs latency"Model optimizationquantization, INT8, FP8, AWQ, GPTQ, pruning, distillation, ONNX, TensorRT, "model compression", LoRA serving, "multi-LoRA" Monitoring AI systems"drift detection", "data drift", "concept drift", Evidently, Arize, WhyLabs, Fiddler, Langfuse, LangSmith, "model monitoring", "prediction logging", "bias monitoring" TTFT or tokens/sec numbers, GPU cost reductions, latency before/after, QPS served. Kindly share the resume to sudhir.pathak@ampstek.com