ML Infrastructure Engineer

Nebius

Amsterdam, Amsterdam

Remote

Who this role is best for

Best suited to mid-level ML engineers with deep GPU performance expertise working in AI cloud infrastructure, offering remote options across Europe and the US.

Best fit for

Engineers who can debug ML workloads at the kernel level
— “Debug and optimise ML workloads to run efficiently on GPU hardware”
Professionals comfortable with system-level GPU performance analysis
— “profile and analyse GPU performance at the system and kernel level”
Candidates with hands-on experience in modern deep learning frameworks
— “Deep experience with modern deep learning frameworks”

Things to consider

Requires deep understanding of GPU stack components like CUDA and NCCL
— “Good understanding of the GPU stack: CUDA,NCCL, drivers”
Must be authorized to work in the country of application
— “Applicants must be authorized to work in the country in which they apply”

How to stand out

Highlight contributions to open-source ML benchmarking tools in your resume
— “Contributions to open-source ML benchmarking tools”
Prepare to discuss specific LLM inference frameworks like vLLM or TensorRT
— “Familiarity with modern LLM inference frameworks (vLLM, SGLang, TensorRT)”
Showcase experience with performance profiling tools in past projects
— “Experience in Python and performance profiling tools”

Pace · Fast PacedCollaboration · HighAutonomy · MediumDecision Impact · TeamLevel · Senior

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

benchmarked gpu performance
optimized ml workloads
developed performance visualization tools

Typical background

phd in computer sciencemasters in machine learningbachelor in electrical engineering

Skills & requirements

Required

Machine-learningDeep-learningGpu-optimizationPerformance-analysisCloud-platformsGpu-architectureDeep-learning-frameworksContainerized-environments

Preferred

Llm-inference-frameworksPython-profiling-toolsCloud-ml-platformsOpen-source-ml-benchmarking

Stack & domain

PythonCudaRocmDockerKubernetesAWSGCPAzure MlNsightNvprofPerfCommunicationAIMLCloud InfrastructureGpuHardwareSoftwareAi/ml Infrastructure

About the role

Original posting from Nebius

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.
The role
We are seeking a highly skilled ML/AI Engineer to join our team to lead and support benchmarking of GPU platforms benchmarking of GPU platforms for machine learning and AI workloads. You will play a critical role in evaluating the performance of GPU-based hardware for various deep learning and AI frameworks, enabling data-driven decisions for platform optimisation and next-generation hardware development.
Your responsibilities will include:
Work closely with hardware, development teams to profile and analyse GPU performance at the system and kernel level.
Evaluate and compare GPU performance across different platforms, architectures, and software stacks (e.g.,CUDA, ROCm).
Debug and optimise ML workloads to run efficiently on GPU hardware, identifying and resolving performance bottlenecks.
Perform acceptance testing acceptance testing for new GPU clusters, ensuring hardware and software meet performance, stability, and compatibility requirements for AI workloads.
Perform experiments across diverse GPU system configurations to assess the impact of varying interconnect strategies and system-level optimisations on performance and scalability.
Develop tools and dashboards to visualise performance metrics visualise performance metrics, bottlenecks, and trends.
Contribute to internal tooling, frameworks, and best practices
We expect you to have:
A profound understanding of theoretical foundations of machine learning
Deep understanding of performance aspects of large neural networks training and inference (data/tensor/context/expert parallelism, offloading, custom kernels, hardware features, attention optimisations, dynamic batching etc.)
Deep experience with modern deep learning frameworks (PyTorch, JAX, Megatron-LM, Tensort-LLM)
Good understanding of the GPU stack: CUDA,NCCL, drivers, and relevant libraries
Familiarity with containerized environments (e.g., Docker, Kubernetes).
Strong communication and ability to work independently
 
Ways to stand out from the crowd:
Familiarity with modern LLM inference frameworks (vLLM, SGLang, TensorRT)
Experience in Python and performance profiling tools (e.g., Nsight, nvprof, perf).
Familiarity with cloud ML platforms like AWS, GCP, Azure ML
Contributions to open-source ML benchmarking tools
Benefits & Perks:
Competitive compensation
Career growth and learning opportunities
Flexibility and work-life balance
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.

Source: Nebius careers