Edge Inference Engineer: Optimize On-Device AI Kernels
Liquid AI
Liquid AI is seeking a Systems Programmer to join their Edge Inference team in San Francisco. In this role, you will implement and optimize inference kernels on various hardware, ensuring efficiency and performance. Ideal candidates have over 5 years of systems programming experience with strong C++ skills and a deep understanding of ML fundamentals. The position offers competitive salary, equity, and comprehensive health benefits. Flexible location options available. #J-18808-Ljbffr Liquid AI
Vacancy posted 2 days ago
Similar jobs that could be interesting for youBased on the Edge Inference Engineer: Optimize On-Device AI Kernels in San Francisco, CA vacancy
- FriendliAI is seeking a GPU Kernel Engineer in San Francisco to design and optimize GPU kernels for AI inference. This role requires expertise in CUDA, C++, and performance-critical systems. You will work on cutting-edge GPU technology and contribute to a highly collaborative...Suggested
$250k
...Edge AI is a production requirement across automotive, robotics,... ...team deploying models on edge devices rebuilds memory management, platform... ..., memory managers that optimize dynamically, observability stacks... ...are doing in the field. Inference latency, memory pressure, thermal...SuggestedForum Ventures
San Francisco, CA4 days ago- ...A leading AI acceleration company in San Francisco is seeking a GPU Kernel Engineer to optimize performance for machine learning models. You will be responsible for designing high-performance GPU kernels and using advanced techniques to boost computation efficiency. Ideal...Suggested
Baseten
San Francisco, CA4 days ago - Mercor is looking for a CUDA Engineering Expert to optimize GPU kernels for performance and efficiency. This remote role requires expertise... .... Join a team that connects talent with leading AI research labs and contribute to cutting-edge GPU technology. #J-18808-Ljbffr MercorSuggestedRemote jobFlexible hours
- ...powers mission‑critical inference for the world's most dynamic AI companies, like... ...to bring cutting‑edge models into production... ...build the platform engineers turn to to ship AI... ...’re seeking a GPU Kernel Engineer to join our... ...AI workloads, optimizing every microsecond of...SuggestedFlexible hours
The Consensus
San Francisco, CA4 days ago - Gravity Engineering Services Pvt Ltd. is looking for an Inference Frameworks and Optimization Engineer to enhance the performance of AI infrastructure. This role involves designing distributed inference... ...you're passionate about cutting-edge AI technologies, we want to hear...
$160k - $230k
About the Role At Together.ai, we are building state-... ...efficient and scalable inference for large language... ...LLMs). Our mission is to optimize inference frameworks,... ...Frameworks and Optimization Engineer to design, develop, and... ..., compiled, efficient kernels. Soft Skills: Strong...Full time$225k
Magic is hiring a Kernel Engineer in San Francisco to design and maintain high-performance kernels that optimize throughput and latency during AI training and inference. The ideal candidate has low-level programming expertise, particularly for AI accelerators like NVIDIA...$95k
...What You’ll Do We’re hiring Edge Engineers to partner closely with our... ...shipping and assembling edge devices to managing full‑scale rollouts... ...hardware challenges, optimizing field workflows, and traveling... ...troubleshooting of cameras, inference pipelines, and data uploads...Remote workWork from homeRelocation packageFlexible hours- MakerMaker, based in San Francisco, is seeking a highly skilled kernel engineer to write and optimize GPU kernels that enhance performance for training and inference. This role involves deep, low-level work to close the significant performance gap that exists in modern...
- ...experienced Robotics Software Engineer focused on embodied AI and bridging the gap... ...teleoperation pipelines, on- and off-device inference, and hands-on lab... ...pipelines directly on the edge hardware. Integrate teleoperation workflows and optimize end-to-end control latency...
Efference
San Francisco, CA1 day ago - Pantera Capital is looking for a Model Performance Engineer in San Francisco, California to optimize model inference speed, cost, and reliability. You will build fine-tuning infrastructure that accelerates the AI team’s processes. The role covers optimizing serving frameworks...
- ...Embedded Software Engineer - Embedded Systems... ...world of physical AI and robotics. We are... ...to own the full on-device software stack for... ...current and future edge devices across a wide... ...features. Debugging and optimizing system performance... ...on experience with kernel driver development...
- ...As a Backend Software Engineer at Droyd, you’ll own core... ...support learning, inference, control, and fleet operations... ...team across robotics, AI, and hardware. Your... ...AI models running on edge devices and GPUs Build and... ...reliability Develop and optimize low-latency streaming...
- A leading AI research firm in San Francisco is seeking a Technical Lead to join its Future... ...evaluating silicon platforms and optimizing model architectures while working in a hybrid... ...and is centered on deploying cutting-edge AI technology responsibly and effectively...Relocation package
- A tech startup focused on AI workloads is seeking a Member... ...Technical Staff to design and optimize inference systems. The role involves... ...should have strong software engineering skills and experience with ML... ...opportunity to contribute to cutting-edge AI technology in a dynamic...
$342k
...demands of advanced AI workloads. The... ...and enable hardware optimized specifically for AI... ...the Role As an Engineer on our hardware optimization... ...work with our kernel, compiler and... ...efficient training and inference on our models. If... ...model across devices, dealing with and...Full timeWork at officeLocal areaRelocation packageFlexible hours- ..., and validation systems that ensure our device software is reliable, testable, and ready... ...standards. About the Role As a Software Engineer, Quality and Developer Tools, you will build... .... About the Company The company is an AI research and deployment company dedicated...Work at officeRelocation package
United States Digital Space LLC
San Francisco, CA4 days ago - Hayden AI Technologies, Inc. is looking for a Senior Firmware Engineer to join the Device Software team in San Francisco, California... ...expertise in Linux kernel and device driver... ...device drivers, optimize performance, and... ...key role in advancing edge AI systems. #J-18808...
- ...groundbreaking vision-based AI, designed for... ...culture can be engineered – but when it... ...software engineer to optimize and deploy ML models... ..., custom CUDA kernels, and low-level systems... .... Beyond inference, you'll profile and... ...robotics, or IoT/edge devices Deep knowledge of...Local area
Humble Robotics
San Francisco, CA19 hours ago - ...powers mission‑critical inference for the world's most dynamic AI companies, like... ...to bring cutting‑edge models into production... ...build the platform engineers turn to to ship AI... ...inference optimizations. THE OPPORTUNITY Networking... .... Optimize Kernels: You will work with...Flexible hours
- Gravity Engineering Services Pvt Ltd. in San Francisco is looking for a specialized engineer to advance the efficiency of ML inference systems. The role encompasses algorithm design, system optimization, and the integration of RL-driven training techniques. Ideal candidates...
- Senior Site Reliability Engineer - AI Infrastructure... ...platform routes training and inference jobs across global... ...from network fabric - kernel - framework. What You’... ...GPU compute clusters optimized for large‑scale training... ...workloads, including device plugins, topology‑aware...Full timeRemote work
$300k
...technology firm in San Francisco seeks a GPU Optimisation Engineer to maximize GPU performance in real-time AI systems. The ideal candidate will possess strong... ...understanding of GPU execution, and a knack for optimizing inference latency for large generative models. With a...Visa sponsorshipRelocation package- Quadric is seeking a Senior Platform Software Engineer in San Francisco, California. In this role, you will optimize neural networks on the Quadric GPNPU, using your expertise... ...optimization. You will influence cutting-edge technology, collaborating with a dedicated team...
- ...unicorn founders and senior engineers with deep expertise in... ...Founding Engineer, ML Inference with deep expertise in... ...inference frameworks, optimizing inference performance,... ...the competitive edge in ultra-low-latency,... ....compile, custom CUDA kernels, and specialized inference...RelocationVisa sponsorshipRelocation package
$160k - $230k
Together AI is seeking an Inference Frameworks and Optimization Engineer in San Francisco, California. The role focuses on designing and optimizing distributed inference engines, ensuring efficient deployment of large language models and vision models. The ideal candidate...$100k - $120k
...models. As training and inference workloads grow, we need kernel‑level innovations to reduce... ...team to architect and optimize low‑level compute kernels... ...team of kernel and system engineers focused on performance-critical... ...deployment in cloud and edge environments Explore OS...- ...Francisco is looking for a motivated software engineer to optimize token processing at every layer of the stack. You will modify inference engines and analyze GPU performance,... ...of LLM mechanics and interests in cutting-edge MLSys research. The company offers benefits...
$325k
About the Team Our Inference team brings OpenAI's most capable research... ...our state-of-the-art AI models, allowing them to do... ...the Role We're hiring engineers to scale and optimize OpenAI's inference infrastructure... ...the stack - from low-level kernel performance to high-level...
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Edge Inference Engineer: Optimize On-Device AI Kernels. Be the first to apply!
