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

Inferactinference provider

San Francisco · onsite · manager

eng-managerinferenceinference-enginesvllm-enginedistributed-inference

posted 6w ago · verified today

Inferactinference provider

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

reliability-sresreinferenceobservabilityvllm-engine

posted 3w ago · verified today

Inferactinference provider

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

amdgpu-kernelsinferenceperformance-engineerrocm-hip

posted 11w ago · verified today

Inferactinference provider

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

tpuinferenceinference-enginesjax-pallasperformance-engineer

posted 11w ago · verified today

Inferactinference provider

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

amdgpu-kernelsinferenceinference-enginesperformance-engineer

posted 11w ago · verified today

Inferactinference provider

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

software-engineerdistributed-inferenceinference-enginesinfiniband-opsnvlink-topology

posted 12w ago · verified today

Inferactinference provider

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

gpu-kernelscudaperformance-engineercpp-langinference

posted 12w ago · verified today

Inferactinference provider

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

vllm-engineinferenceinference-engineskv-cache-systemspython-lang

posted 12w ago · verified today

Inferactinference provider

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

cluster-datacentergo-langgpu-genericinferencekubernetes-ops

posted 12w ago · verified today

Inferactinference provider

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

inferenceinference-enginespython-langvllm-enginesoftware-engineer

posted 3mo ago · verified today

Inferactinference provider

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

tpuinference-enginesjax-pallasperformance-engineerxla-compiler

posted 3mo ago · verified today

Inferactinference provider

Remote · remote · unknown

gpu-kernelsinferenceinference-enginesvllm-enginedistributed-inference

posted 7mo ago · verified today

Inferactinference provider

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

kubernetes-opssoftware-engineercluster-datacentergo-langinference

posted 7mo ago · verified today

Inferactinference provider

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

distributed-inferenceinference-enginesvllm-enginecpp-langgo-lang

posted 7mo ago · verified today

FriendliAIinference provider

San Francisco · hybrid · senior

cluster-datacentergpu-genericinferencekubernetes-opsml-platform

posted 5w ago · verified today

FriendliAIinference provider

Seoul · onsite · senior

kubernetes-opssoftware-engineernetwork-fabricscheduling-orchestrationcluster-datacenter

posted 5w ago · verified today

FriendliAIinference provider

Seoul · onsite · mid

amdcpp-langcudacutlass-cutegpu-kernels

posted 4mo ago · verified today

FriendliAIinference provider

Seoul · onsite · senior

gpu-kernelsinferencecpp-langinference-enginespython-lang

posted 4mo ago · verified today

FriendliAIinference provider

San Francisco · hybrid · mid

amdcpp-langcudagpu-genericgpu-kernels

posted 6mo ago · verified today

FriendliAIinference provider

San Francisco · hybrid · mid

solutions-architectgpu-kernelsinference-engineskubernetes-opsobservability

posted 6mo ago · verified today

FriendliAIinference provider

San Francisco · hybrid · senior

cpp-langgpu-kernelsinferenceinference-enginespython-lang

posted 6mo ago · verified today

NexGen Cloudneocloud

London · London, England, United Kingdom, UK - Remote +1 more · remote · unknown

solutions-architectcudacudnn-libdeepspeed-libgpu-generic

posted 8w ago · verified today

NexGen Cloudneocloud

London · Nottingham · senior

kubernetes-opscluster-datacentergpu-genericnvidiascheduling-orchestration

posted 5mo ago · verified today

NexGen Cloudneocloud

Canada - Remote · Quebec, Canada · unknown

kubernetes-opscluster-datacenterdatacenter-engineergpu-genericreliability-sre

posted 14d ago · verified today

NexGen Cloudneocloud

UK - Remote · remote · senior

cudanvidiacluster-datacenternetwork-fabriccudnn-lib

posted 4mo ago · verified today

San Francisco Compute Companyneocloud

Remote · San Francisco, CA · hybrid · $220K–$300K/year · senior

cluster-datacenterdatacenter-engineergpu-genericnetwork-fabricinfiniband-ops

posted 2d ago · verified today

Prime Intellectneocloud

Remote · San Francisco · unknown

cudapytorch-distreinforcement-learningresearch-engineertriton-lang

posted 10w ago · verified today

Prime Intellectneocloud

San Francisco · onsite · unknown

kubernetes-opsml-platformfine-tuninggpu-genericnvidia

posted 10w ago · verified today

Prime Intellectneocloud

San Francisco · unknown

post-trainingreinforcement-learningresearch-engineerevaluationml-platform

posted 10w ago · verified today

Prime Intellectneocloud

Remote · San Francisco · hybrid · unknown

cluster-datacentergpu-genericinfiniband-opskubernetes-opsnetwork-fabric

posted 10w ago · verified today