[All remote jobs](https://jobicy.com/jobs.md)[![Nebius logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/06/d90c0566-221.webp)](https://jobicy.com/company/nebius.md)[Nebius](https://jobicy.com/company/nebius.md) # System Engineer (Token Factory) AI Summary Nebius is seeking a systems engineer for Token Factory, its large-scale GPU-cloud inference platform. The role develops and optimizes low-level kernels and runtime components for AI inference across modern GPU architectures. Key work includes profiling CPU/GPU performance, debugging hardware- and system-level bottlenecks, and integrating support for Hopper, Blackwell, and Rubin platforms. The engineer will collaborate with machine-learning and backend teams to improve end-to-end inference efficiency and reliability. Strong C++ or GPU programming expertise, systems software knowledge, and performance-analysis experience are central to success.[Apply for this job](#job-application)[View company](https://jobicy.com/company/nebius.md)ShareRemote from[USA](https://jobicy.com/job-region/usa.md), [Europe](https://jobicy.com/job-region/europe.md)SalaryUndisclosedDepartment[Software Engineering](https://jobicy.com/categories/engineering.md)EmploymentFull TimeExperienceOpen levelPublished3 Nov 2026Apply before3 Dec 2026Listing views35Application actions1Application toolkit ## Make your next move. Prepare your resume, explore your fit, and draft a cover letter for this opportunity. Opportunity details ## About this role. About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D. About the role: Token Factory is a part of Nebius Cloud, one of the world’s largest GPU clouds, running tens of thousands of GPUs. We are building an inference platform that makes every kind of foundation model — text, vision, audio, and emerging multimodal architectures — fast, reliable, and effortless to deploy at massive scale. Responsibilities: * Develop and optimize low-level kernels and runtime components for AI inference * Improve performance of inference engines GPU platforms * Profile and debug system-level and hardware-level performance issues * Integrate support for new hardware architectures (Hopper, Blackwell, Rubin) * Collaborate with ML and backend teams to optimize end-to-end execution Required Qualifications: * Strong proficiency in C++, OR expertise in GPU programming with a focus on low-level high-performance coding and memory management * Experience in GPU programming or systems-level software development, e.g. operating system internals, kernel modules, or device drivers * Hands-on experience with profiling and debugging tools to identify performance issues on both CPUs and GPUs, and the ability to optimize code based on those findings. * Solid understanding of CPU/GPU architecture and memory hierarchy Preferred Qualifications: * Experience with GPU computing programming: CUDA, ROCm, CUTLASS, Cute, ThunderKittens, Triton, Pallas, Mosaic GPU * Familiarity with ML inference runtimes (e.g. TensorRT, TVM) * Knowledge of Linux internals, drivers, or compiler toolchains * Experience with tools like perf, VTune, Nsight, or ROCm profiler * Familiarity with popular inference engines (e.g. such as vLLM, sglang, TGI) We conduct coding interviews as part of the process. Benefits & Perks: * Competitive compensation * Career growth and learning opportunities * Flexibility and ownership * Collaborative and innovative culture * Opportunity to work on impactful AI projects * International environment and talented teams What’s it like to work at Nebius: Fast moving – Bold thinking – Constant growth – Meaningful impact – Trust and real ownership – Opportunity to shape the future of AI Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire. If you need accommodations during the application process, please let us know. Show more [Apply now >](https://jobicy.com/jobs/158738-system-engineer-token-factory.md) > Annual salary information is not provided for this position. Explore salary ranges for similar roles in our [Salary Directory ›](https://jobicy.com/salaries.md) * ![Upload CV](data:image/svg+xml;base64,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) ### Upload your resume now To unlock remote work opportunities and be discovered by global employers. This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content. ## Role DNA A quick view of the complexity, pace, ownership and collaboration implied by the job description. ### Job Complexity 5/5EasyHard ### Pace & Pressure 5/5RelaxedFast-paced ### Autonomy Level 4/5GuidedFull ownership ### Communication Load 4/5IndependentCollaborative AI insightThis is a highly specialized performance-engineering role requiring deep understanding of GPU architecture, memory hierarchies, low-level programming, and AI inference systems. The rapidly evolving hardware and large-scale production environment add substantial technical complexity. ## Salary analysis Estimated compensation compared with the broader US market for similar roles. Estimated job median (per year)Market rate$190,000US market range (per year)$160k–$230k0$253.00k AI insightThe yearly pay period is inferred from the job context; it was not explicitly stated by the employer. No employer salary range is disclosed. The annual USD figures are AI estimates for a senior-level GPU systems and AI-inference performance engineer in the US market; the yearly cadence is inferred from the full-time professional role and US market context. ## Core skills Skills and capabilities most closely associated with this opportunity. [C++](https://jobicy.com/jobs?search_keywords=C%2B%2B.md)[GPU programming](https://jobicy.com/jobs?search_keywords=GPU%20programming.md)[CUDA](https://jobicy.com/jobs?search_keywords=CUDA.md)[ROCm](https://jobicy.com/jobs?search_keywords=ROCm.md)[GPU kernel optimization](https://jobicy.com/jobs?search_keywords=GPU%20kernel%20optimization.md)[AI inference](https://jobicy.com/jobs?search_keywords=AI%20inference.md)[Performance profiling](https://jobicy.com/jobs?search_keywords=Performance%20profiling.md)[CPU/GPU architecture](https://jobicy.com/jobs?search_keywords=CPUGPU%20architecture.md)[Memory management](https://jobicy.com/jobs?search_keywords=Memory%20management.md)[Linux internals](https://jobicy.com/jobs?search_keywords=Linux%20internals.md)[Systems programming](https://jobicy.com/jobs?search_keywords=Systems%20programming.md)[Nsight](https://jobicy.com/jobs?search_keywords=Nsight.md)[TensorRT](https://jobicy.com/jobs?search_keywords=TensorRT.md)[vLLM](https://jobicy.com/jobs?search_keywords=vLLM.md)[Debugging](https://jobicy.com/jobs?search_keywords=Debugging.md) Sample interview questionsHow would you investigate a GPU inference workload that has lower throughput than expected?I would first establish a baseline and collect traces with tools such as Nsight Systems and Nsight Compute. I would examine kernel execution, memory transfers, occupancy, warp stalls, memory bandwidth, and CPU-side scheduling, then prioritize the dominant bottleneck and validate each optimization with repeatable benchmarks. What factors influence memory performance in a CUDA kernel? Important factors include access coalescing, alignment, cache behavior, shared-memory bank conflicts, register pressure, occupancy, and unnecessary global-memory traffic. I would structure data layouts and thread access patterns to improve locality while balancing register use and parallelism. How would you optimize an inference runtime for a newly released GPU architecture? I would review its compute, memory, and tensor-core capabilities, benchmark representative model workloads, and profile existing kernels to identify architecture-specific limits. Then I would tune launch configurations, memory movement, precision paths, and kernel implementations, validating correctness and performance across model sizes and batch profiles. Describe how CPU-side behavior can affect GPU inference performance. CPU scheduling, request batching, memory allocation, synchronization, launch overhead, data preparation, and host-to-device transfers can all starve the GPU or increase tail latency. I would profile the full pipeline rather than individual kernels and optimize the critical end-to-end path. How would you work with ML and backend engineers when a model has poor production latency? I would agree on workload definitions and service-level targets, collect production-like traces, and separate model, runtime, and serving bottlenecks. I would communicate evidence-based trade-offs such as batching, quantization, graph capture, or scheduling changes, then jointly validate improvements against throughput, latency, quality, and reliability requirements. Next step ## Apply now. Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information. Keep exploring ## Related remote jobs. * ![ecosio logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/eec17a98-221.png) ecosio Nov 3 New ### [Test Automation Engineer (f/m/d)](https://jobicy.com/jobs/158729-test-automation-engineer-f-m-d.md) ecosio is a fast-growing, innovative service company and a leading provider of B2B integration, specialising in electronic data interchange (EDI), Web EDI and e-invoicing. ecosio is part of Vertex, Inc.,… * ![Fieldguide logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/08/afa73463-221.png) Fieldguide Nov 3 New ### [Software Engineer, Quality & Automation](https://jobicy.com/jobs/158677-software-engineer-quality-automation.md) About Us Fieldguide is establishing a new state of trust for global commerce and capital markets by automating and streamlining the work of assurance and audit practitioners — specifically in… * ![Mercury logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2023/11/dfb1112a-221.jpeg) Mercury Nov 3 New ### [Open Call for Founders / Founding Teams – Product Management and Engineering](https://jobicy.com/jobs/158675-open-call-for-founders-founding-teams-product-management-and-engineering.md) Open call for Founders / Founding Teams (Product Management / Engineering roles) In 1973 at Xerox PARC, Bob Metcalfe sketched a way for many computers to share a single wire… * ![Mercury logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2023/11/dfb1112a-221.jpeg) Mercury Nov 3 New ### [Marketing Engineer](https://jobicy.com/jobs/158669-marketing-engineer-2.md) Good marketing depends on systems that work: conversion signals that arrive accurately, audiences that stay current, and tools that make new ideas easier to try. We’re hiring a Marketing Engineer… * ![Canonical logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/b4d068a9-221-1.png) Canonical Nov 3 New ### [NetSuite Administrator](https://jobicy.com/jobs/158643-netsuite-administrator.md) Canonical is a leading provider of open-source software and operating systems for global enterprise and technology markets. Our platform, Ubuntu, is very widely used in breakthrough enterprise initiatives such as… * ![Monzo logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/5b4c0ec3-221.jpg) Monzo Nov 3 New ### [Staff Backend Engineer](https://jobicy.com/jobs/158639-staff-backend-engineer-4.md) 🚀 We’re on a mission to make money work for everyone. We’re waving goodbye to the complicated and confusing ways of traditional banking. After starting as a prepaid card, our… * ![Canonical logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/b4d068a9-221-1.png) Canonical Nov 3 New ### [Lead Data Governance Engineer](https://jobicy.com/jobs/158612-lead-data-governance-engineer.md) Canonical is a leading provider of open-source software and operating systems for global enterprise and technology markets. Our platform, Ubuntu, is very widely used in breakthrough enterprise initiatives such as… * ![Canonical logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/b4d068a9-221-1.png) Canonical Nov 3 New ### [Kernel Build Automation Engineer – Ubuntu Linux](https://jobicy.com/jobs/158610-kernel-build-automation-engineer-ubuntu-linux.md) Ubuntu Linux is one of the most widely used Linux distributions in the world today and one of the top contributing factors to its popularity is its wide availability and… * ![Vonage logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/1bac058d-221.jpg) Vonage Nov 3 New ### [Senior Engineering Manager](https://jobicy.com/jobs/158601-senior-engineering-manager-3.md) Join Vonage and help us innovate cloud communications for businesses worldwide! Why this role matters: Vonage’s API Business Unit is building a modern, lean architecture practice in a small central… * ![Canonical logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/b4d068a9-221-1.png) Canonical Nov 3 New ### [Juju Software Engineer (Go)](https://jobicy.com/jobs/158600-juju-software-engineer-go.md) Canonical is a leading provider of open source software and operating systems to the global enterprise and technology markets. Our platform, Ubuntu, is very widely used in breakthrough enterprise initiatives… [Browse all jobs](https://jobicy.com/jobs.md)