Senior Machine Learning Engineer
Core
Building fast, reliable, and cost-efficient inference services for frontier LLM/VLM models, optimizing from model artifacts through production deployment.
Role type
Senior IC machine learning engineer (inference optimization)
Builds
Production inference engines and serving backends for frontier AI models
Domain
Cloud infrastructure for AI / Large Language Models (LLM) / Vision Language Models (VLM)
Deliverable
production ML models
Required skills
Python, PyTorch, LLM/VLM inference optimization, transformer inference bottlenecks, latency/throughput/cost tradeoff analysis, inference engine configuration
Preferred skills
Model compression (quantization, distillation), speculative decoding, KV-cache optimization, CUDA/Triton familiarity, open-source contributions to inference stacks
Technologies
vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, KServe, PyTorch
Responsibilities
Optimize LLM/VLM endpoints for latency, throughput, memory efficiency, and cost per token; Deploy, configure, and benchmark inference engines; Build reproducible benchmark harnesses; Debug model quality or performance regressions; Partner with kernel and platform engineers to diagnose bottlenecks
Seniority
Senior, hands-on IC
