AI infrastructure roles, filterable by the stack you actually work on.

Distributed training · inference serving · GPU fleets · network fabric — aggregated straight from company boards, never a copy of a copy.

1296 open roles · 85 companies · last verified today

40 roles

Sort by

speculative-decoding ✕

Senior Software Engineer, Inference

CoreWeaveneocloud

Bellevue, WA · Sunnyvale, CA · $152K–$204K/year est. · senior

cuda distributed-inference go-lang gpu-generic gpu-kernels

posted 11mo ago · verified today

Senior Software Developer: Models Team (Token Factory)

Nebiusneocloud

Amsterdam · Amsterdam, Netherlands +14 more · remote · senior

go-lang inference inference-engines kv-cache-systems python-lang

posted 11w ago · verified today

Senior ML Engineer (Token Factory)

Nebiusneocloud

Amsterdam, Netherlands · Berlin, Germany +6 more · remote · senior

gpu-generic inference inference-engines ml-platform performance-engineer

posted 6mo ago · verified today

Senior ML Engineer (Token Factory)

Nebiusneocloud

Germany · Israel +5 more · remote · senior

fine-tuning inference distributed-inference inference-engines performance-engineer

posted 7mo ago · verified today

Senior Machine Learning Engineer, LLM Inference Optimization

Nebiusneocloud

Palo Alto, California, United States · San Francisco Bay Area · $195K–$262K · senior

inference inference-engines python-lang quantization vllm-engine

posted 7w ago · verified today

Senior Applied Scientist, Efficient LLM Inference & Model Optimization

Nebiusneocloud

Palo Alto, California, United States · San Francisco Bay Area · $195K–$262K · senior

research-engineer cuda inference python-lang triton-lang

posted 7w ago · verified today

Principal ML Solutions Architect - Token Factory

Nebiusneocloud

United States · $208K–$261K · staff plus

solutions-architect fine-tuning inference inference-engines kv-cache-systems

posted 11w ago · verified today

Forward Deployed Engineer, Ecosystem

Nebiusneocloud

Remote - United States · remote · $180K–$224K · senior

python-lang sglang-engine solutions-architect tensorrt-stack vllm-engine

posted 4mo ago · verified today

Machine Learning Engineer - Inference

Together AIneocloud

San Francisco · $200K–$300K/year est. · mid

inference inference-engines python-lang pytorch-dist software-engineer

posted 27mo ago · verified today

Forward Deployed Engineer (Inference & Post-Training) - Mandarin Speaking

Together AIneocloud

Remote · Singapore · unknown

fine-tuning inference inference-engines kv-cache-systems post-training

posted 6w ago · verified today