Member of Technical Staff - GPU Inference Engineer
liquid-ai
Role: Member of Technical Staff - GPU Inference Engineer
Team: Research & Engineering
Location: San Francisco; Boston; Remote
Location Type: Hybrid
Employment Type: Full-time
About Liquid AI
Spun out of MIT CSAIL, we build general-purpose AI systems that run efficiently across deployment targets, from data center accelerators to on-device hardware, ensuring low latency, minimal memory usage, privacy, and reliability. We partner with enterprises across consumer electronics, automotive, life sciences, and financial services. We are scaling rapidly and need exceptional people to help us get there.
The Opportunity
GPU inference sits underneath much of how we build and ship models at Liquid. Evaluation runs, synthetic data generation, and our API service all depend on how fast and how cheaply we can serve Liquid Foundation Models on GPUs, and demand for that work is growing. You will join the small team that owns our GPU serving stack, built on vLLM and SGLang, and make it faster and cheaper to run.
This is a high-ownership role: you will be pointed at whichever inference bottleneck matters most and carry it from profiling to a benchmarked result. The work sits at the serving-framework level rather than in custom CUDA kernels, which is a separate role on the team.
What We're Looking For
We need someone who:
Reasons from first principles: Explains why a workload is slow before changing it, working from what the model and the GPU are actually doing rather than from framework defaults.
Picks up the next problem and owns it: Moves from evaluation throughput to data generation to API serving as priorities shift, and takes each one through to a measured result.
Makes other teams faster: Works directly with the researchers and engineers who depend on inference, and treats their throughput as the result that counts.
The Work
Own and improve our GPU serving stack on vLLM and SGLang, from configuration and scheduling choices to changes in the frameworks themselves
Speed up large-scale evaluation and synthetic data generation, and design the inference pipelines those workloads run on
Select, profile, and benchmark the inference engine behind our API service, and adapt the API layer around it
Integrate Liquid Foundation Models into vLLM, SGLang, and Hugging Face Transformers, and maintain those public integrations as models and frameworks change
Diagnose throughput and latency problems alongside the researchers and serving engineers who hit them
What you'll need:
Hands-on experience running LLM inference on GPUs with a serving framework such as vLLM or SGLang, beyond default configuration
First-principles understanding of LLM inference: the transformer forward pass, autoregressive decoding on a GPU, and the latency, throughput, and memory trade-offs that follow
Solid grasp of GPU fundamentals as they bear on inference. You do not need to have written CUDA kernels
Experience profiling and benchmarking inference workloads and acting on what the numbers show
Strong Python and PyTorch, and comfort reading and changing large open-source codebases
Helpful, not required:
Merged contributions to vLLM, SGLang, or FlashInfer
Lower-level GPU optimization experience, such as CUDA or Triton kernels
Experience building high-throughput batch inference for evaluation or synthetic data generation
What Success Looks Like (Year One)
Evaluation and synthetic data generation run measurably faster and at lower cost per token on the same hardware, freeing GPU capacity for other work
The inference engine and configuration behind our API service are chosen on benchmark evidence, and have been profiled and tuned for latency and throughput
Liquid models run correctly and efficiently in the public serving frameworks and libraries our users rely on, including vLLM, SGLang, and Transformers
What We Offer
Problems standard stacks don't solve: Our hybrid architectures do not drop into off-the-shelf serving frameworks unchanged, and the inference you speed up feeds how every Liquid model is evaluated and trained. High ownership from day one.
Compensation & Equity: Competitive base salary plus equity, so you share in what we build. Final offers reflect skills, experience, and location.
Time Off: Unlimited PTO, plus company-wide Refill Days, long weekends when the whole company rests together.
Health & Wellbeing: Comprehensive health coverage, with details varying by location.
Paid Leave: Paid leave for pregnancy, parenting, medical needs, and caring for family.
- ...also lowers the barrier to creating engineered threats and AI-generated bioweapons.... ...defend. About the Role As a Member of Technical Staff, Inference at Radical Numerics, you will build... ...inference, kernel optimization, GPU systems, and performance engineering...SuggestedFull timeLocal area
- ...efficient software for inference (processing LLM tokens)... ...state-of-the-art inference engines like vLLM and SGLang,... ...every microsecond of GPU time spent during a forward... ...interpersonal and technical communication. Please don... ...whiteboard with a team member and work through a...SuggestedFull timeWork at office
$285k - $315k
...re looking for researchers, engineers and organizations who agree... ...We build the fastest GPU compiler in the world. Most... ...kernels. We're hiring a Member of Technical Staff for GPU Compiler Engineering... ...passes to optimize training and inference workloads You'll work in...SuggestedFull timeWork at officeImmediate startRelocation package- ...for fast, efficient AI inference. We combine large-... ...our team access to technical problems spanning frontier... ...the role As a Member of Technical Staff, you will... ...distributed systems engineers when necessary Develop... ...Experience profiling GPU or accelerator workloads...SuggestedFull time
- ...novel model architectures that require GPU performance engineering beyond what standard frameworks can... ...across training, post-training, and inference. Working closely with researchers and... ...production deployment. Communicates technical decisions clearly: You explain your...SuggestedFull time
$200k - $400k
...Overview Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and... ...Experience supporting AI inference, model serving, ML infrastructure, GPU workloads, or other latency-sensitive, high-throughput...Full timeRemote workVisa sponsorship$200k - $300k
...Description Job Description Member of Technical Staff Company: Confidential —... ...serverless and dedicated inference for open-source LLMs at the... ...agents to write and tune GPU kernels across heterogeneous... ...Bring ~1-6 years of software engineering focused on systems close to...Full timeInternshipH1bWork at officeOverseasVisa sponsorship- ...inputs that are unimportant, reducing inference costs for scale-ups and enterprises that... ...research and product focus. As a Member of Technical Staff on our infrastructure team, you'll own... ...global low-latency, high-throughput GPU ML inference infra that sits in the critical...Full timeVisa sponsorship
- ...global AI compute liquid. We bring fragmented, heterogeneous GPU capacity together into one unified, productive platform, making... ...to build with you. About the Role We're looking for an Inference Engineer to build inference capabilities on top of Forge, our unified...Full time
- ...want to accomplish. What you'll do Build and optimize the inference stack that runs personal AI models locally on Core. Improve... ...languages, alongside proficiency in Python. Familiarity with GPU architecture, memory management, and performance profiling. Experience...Full time
- ...models end-to-end. The Role We are looking for an engineer to own the inference systems that power our models in production and research. You... ...deployment Optimize inference performance across GPU and accelerator hardware - maximizing FLOPs utilization, memory...Full time
- ...and CERN. We look for infrastructure engineers who are excited to tackle unsolved... ...Responsibilities Your mission is to make inference so fast and cheap that evaluation never gates... ...Understanding of distributed compute, GPU parallelism, and hardware-aware optimization...Full time
- ...Job Description – Member of Technical Staff (Inference) Location: San Francisco, CA (on-site, 5 days a week, in our San Francisco office) About... ...independent AI benchmarking company. We support labs, engineers and enterprises to understand AI capabilities and make...Full timeWork at officeShift work
- ...Perplexity is looking for a technical program manager to be the connective... ...tissue between our model providers, engineering, and product teams, driving our core inference platform forward. Perplexity... ...'s scale Partner with GPU capacity and compute teams to reconcile...Full timeShift work
$150k - $300k
...We're hiring for multiple GPU Infrastructure positions: one... ...one based in the USA. Core Technical Responsibilities This customer... ...strategies for LLM training, inference, and HPC workloads Present... ...with our world-class engineering team while having direct impact...Remote jobFull timeWork at officeVisa sponsorshipRelocation packageFlexible hours- ...and Suno. They rely on Modal for instant GPU access, sub-second container starts, and... ..., so it's simple to serve low-latency inference, fine-tune models, and access production... ...international olympiad medalists, and experienced engineering and product leaders with decades of...Full timeImmediate startRemote work
$275k
...domain-specific RL, ultra-long context, and inference-time compute to achieve this goal. About the role As a Research Engineer on the Inference & RL Systems team, you... ...and eliminate performance bottlenecks across GPU, networking, and storage layers Collaborate...Full timeRelocationVisa sponsorship- ...designed for fast, efficient AI inference. We combine large-scale... ...giving our team access to technical problems spanning frontier... ...About the role As a Member of Technical Staff focused on ML Systems, you... ..., and distributed systems engineers to optimize the full...Full time
$200k - $400k
...simulating a society means running inference over populations of agents,... ...About the Role As a Member of Technical Staff in ML Systems, you will... ...to find where the FLOPs and GPU memory are going, and... ...run. We are looking for engineers who find it gratifying to see...Full timeLive inFlexible hours- ...are looking for exceptional engineers to help build the... .... The Role We are hiring a Member of Technical Staff to lead reinforcement learning... ...rollout generation across multi-GPU environments Improve training... ...or high-throughput inference systems Familiarity with supervised...
$200k - $400k
...Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded... ...years to build. About the Role We're looking for an AMD GPU kernel engineer to make vLLM a first-class inference engine...Full timeRemote workVisa sponsorship- ...scientists, PhDs, creatives, technologists, and engineers working together to transform healthcare.... ...role in building and optimizing the core inference infrastructure that powers our machine... ...compute-heavy workflows and enhance GPU utilization for ML workloads. Build a...Hourly payFull timeFlexible hours
- ...modern accelerators, including direct technical work with silicon vendors. You know GPU architecture and how logical... ...and latency measurement, and the inference problems underneath geolocating compute... ...environments and security engineering. Building and defending hardened...Part timeLocal area
- ...Space, Solidworks, and more. About the Role Member of Technical Staff is a generalist position where you will collaborate... ...recipes using pipeline RL and make optimizations for max gpu utilization Context Engineering. Automate ingestion of extremely unstructured and...
$2,000 per month
...anyone in the world. Job Summary We’re hiring Members of Technical Staff — the general research/engineering seat. If you have a seriously compelling research... ...scale pretraining, dataset curation, or distributed GPU training Familiarity with egocentric / first-person...Work at officeRelocation package- ...are looking for a Performance Engineer to make World Labs’ models... ...eliminate them. Your ownership is technical and concrete: the throughput... ...What You Will Do Optimize inference and serving end to end —... ...production scale. Write and tune GPU kernels (CUDA, Triton) for...Full timeWork at officeVisa sponsorshipWork visaRelocation packageFlexible hours
- ...and CERN. We look for infrastructure engineers who are excited to tackle unsolved... ...training, evaluation, serving — runs on our GPU fleet. Your mission is to design, build,... ...quotas, and multi-tenancy across training and inference workloads Build software that...Full time
- ...designed for fast, efficient AI inference. We combine large-scale... ...giving our team access to technical problems spanning frontier... ...About the role As a Member of Technical Staff, you will build the... ...networking, and infrastructure engineers to connect the full...Full time
- ...and Suno. They rely on Modal for instant GPU access, sub-second container starts, and... ..., so it's simple to serve low-latency inference, fine-tune models, and access production... ...international olympiad medalists, and experienced engineering and product leaders with decades of...Full time
$200k - $400k
...Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded... ...and disaggregated inference architecture. Familiarity with GPU programming models and memory hierarchies. Knowledge of GPU...Full timeRemote workVisa sponsorship
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Member of Technical Staff - GPU Inference Engineer. Be the first to apply!
- helpdesk support technician San Francisco, CA
- tech assistant San Francisco, CA
- technical support assistant San Francisco, CA
- technical analyst San Francisco, CA
- desktop support analyst San Francisco, CA
- user support analyst San Francisco, CA
- support technician San Francisco, CA
- product support technician San Francisco, CA
- mri tech aide San Francisco, CA
- technical support analyst San Francisco, CA


