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

Together AIneocloud

San Francisco · junior

inferenceinference-enginespython-langresearch-engineercuda

posted 6w ago · verified 3d ago

Together AIneocloud

San Francisco · junior

distributed-inferenceinferenceinference-enginesresearch-engineercuda

posted 6w ago · verified 3d ago

Modalinference provider

San Francisco · onsite · $300K–$350K/year · manager

eng-managerinferenceinference-enginesgpu-genericlinux-kernel

posted 6w ago · verified 3d ago

Nscaleneocloud

Houston · New York +2 more · $220K–$330K · staff plus

inferenceinference-engineskv-cache-systemspost-trainingpython-lang

posted 6w ago · verified 3d ago

Amazon (AWS)hyperscaler

Seattle, Washington, USA · onsite · senior

inference-enginessoftware-engineersglang-enginetrainiumvllm-engine

posted 7w ago · verified 3d ago

Inferactinference provider

San Francisco · onsite · junior

amdcudagpu-kernelsinferenceinference-engines

posted 6w ago · verified 3d ago

DeepInfrainference provider

Palo Alto, United States · onsite · unknown

inferenceinference-enginesnvidiapython-langsolutions-architect

posted 11w ago · verified 3d ago

Fireworks AIinference provider

New York · San Mateo · hybrid · $200K–$230K/year · unknown

scheduling-orchestrationcpp-langnetwork-fabricpython-langstorage-checkpointing

posted 7w ago · verified 3d ago

Together AIneocloud

San Francisco · $270K–$300K/year est. · senior

inference-engineskv-cache-systemspython-langspeculative-decodinginference

posted 5mo ago · verified 3d ago

ElevenLabsai startup

Bulgaria · Poland +2 more · remote · unknown

inferenceinference-enginesresearch-engineercudagpu-generic

posted 9w ago · verified 3d ago

Coherefrontier lab

Montreal · New York +2 more · remote · senior

cpp-langgpu-genericinferenceinference-enginesperformance-engineer

posted 11mo ago · verified 3d ago

Inferactinference provider

Remote · remote · unknown

inferenceinference-enginesvllm-enginepython-langsoftware-engineer

posted 8w ago · verified 3d ago

Inferactinference provider

San Francisco · onsite · $200K–$400K/year · unknown

amdgpu-kernelsinferenceperformance-engineerrocm-hip

posted 4mo ago · verified 3d ago

Inferactinference provider

Singapore · onsite · 200K–400K SGD/year · unknown

tpuinferenceinference-enginesjax-pallasperformance-engineer

posted 4mo ago · verified 3d ago

Inferactinference provider

Singapore · onsite · 200K–400K SGD/year · unknown

amdgpu-kernelsinferenceinference-enginesperformance-engineer

posted 4mo ago · verified 3d ago

Inferactinference provider

Singapore · onsite · 200K–400K SGD/year · unknown

vllm-engineinferenceinference-engineskv-cache-systemspython-lang

posted 4mo ago · verified 3d ago

Inferactinference provider

San Francisco · onsite · $200K–$400K/year · unknown

inferenceinference-enginespython-langvllm-enginesoftware-engineer

posted 4mo ago · verified 3d ago

Inferactinference provider

San Francisco · onsite · $200K–$400K/year · unknown

tpuinference-enginesjax-pallasperformance-engineerxla-compiler

posted 4mo ago · verified 3d ago

Thinking Machines Labfrontier lab

San Francisco · onsite · unknown

reinforcement-learningpython-langresearch-engineerinference-enginesdistributed-inference

posted 10w ago · verified 3d ago

Amazon (AWS)hyperscaler

Boston, Massachusetts, USA · Seattle, Washington, USA +1 more · onsite · senior

gpu-kernelsinferenceinference-engineskv-cache-systemsperformance-engineer

posted 9w ago · verified 3d ago

OpenAIfrontier lab

San Francisco · hybrid · $266K–$445K/year · unknown

software-engineerinference-enginesinferencekv-cache-systemsscheduling-orchestration

posted 9w ago · verified 3d ago

Nebiusneocloud

Remote - United States · United States · remote · $228K–$285K · manager

eng-managerfine-tuninginferenceinference-engineskubernetes-ops

posted 10w ago · verified 3d ago

Amazon (AWS)hyperscaler

Cupertino, California, USA · onsite · unknown

cpp-langdistributed-inferencenetwork-fabricsoftware-engineerkv-cache-systems

posted 4w ago · verified 3d ago

Amazon (AWS)hyperscaler

Cupertino, California, USA · Seattle, Washington, USA · onsite · senior

cpp-langnetwork-fabricsoftware-engineercollectivesdistributed-inference

posted 3mo ago · verified 3d ago

Amazon (AWS)hyperscaler

Tel Aviv-Yafo, Tel Aviv, ISR · onsite · mid

cpp-langsoftware-engineercustom-asicdistributed-inferencegpu-kernels

posted 12w ago · verified 3d ago

Amazon (AWS)hyperscaler

Boston, Massachusetts, USA · Seattle, Washington, USA +1 more · onsite · senior

cudacutlass-cutedistributed-inferenceevaluationflash-attention

posted 10w ago · verified 3d ago

Amazon (AWS)hyperscaler

Herndon, Virginia, USA · New York, New York, USA +1 more · onsite · senior

solutions-architectgpu-genericinference-enginesmodel-parallelismtraining-frameworks

posted 4mo ago · verified 3d ago

Perplexityai startup

London · mid

cudagpu-kernelsinferenceinference-engineskv-cache-systems

posted 6mo ago · verified 3d ago

Perplexityai startup

New York City · Palo Alto +1 more · $220K–$485K/year · mid

cudagpu-kernelsinferenceinference-enginescutlass-cute

posted 6mo ago · verified 3d ago

Cerebraschip vendor

Sunnyvale, CA · Toronto, CAN · hybrid · staff plus

inferenceinference-engineskv-cache-systemsperformance-engineerrocm-hip

posted 10d ago · verified 3d ago