Nebius
Senior Backend Developer (Token Factory)(m/w/x)
Full-timeWith HomeofficeSenior
Berlin
New Job?Nejo!
Your personal AI career agent
NENebius
Senior ML Engineer - Token Factory(m/w/x)
Berlin
Full-timeWith Home OfficeSenior
AI/ML
Data Science
Nejo AI Summary
Optimizing LLM inference performance, implementing novel speculative decoding architectures at cloud computing provider for global AI. Experience profiling GPU workloads and GPU memory hierarchy understanding required. Flexible working arrangements.
Requirements
- Understanding of machine learning foundations
- Experience profiling GPU workloads
- Understanding of GPU memory hierarchy
- Familiarity with LLM architectures
- Understanding of neural network training
- Strong software engineering skills
- Experience with deep learning frameworks
- Proficiency in CI/CD and versioning
- Strong communication and leadership abilities
- Experience with open-source inference engines
- Experience with kernel languages
- Track record of delivering products
- Experience developing large distributed systems
- Open-source projects showcasing engineering prowess
- Excellent command of English language
Tasks
- Identify LLM inference bottlenecks
- Drive production speedups
- Maximize performance for LLM architectures
- Support and optimize inference engines
- Implement novel speculative decoding architectures
- Optimize dense and MoE components
- Contribute to open-source inference engines
- Design low-precision training pipelines
- Productionize FP8 and NVFP4 inference
- Improve throughput and cost-efficiency
Work Experience
- approx. 4 - 6 years
Education
- Bachelor's degreeOR
- Master's degree
Languages
- English – Business Fluent
Tools & Technologies
- Nsight
- PyTorch profiler
- Python
- CI/CD
- vLLM
- SGLang
- TensorRT-LLM
- Triton
- Cute
- CUTLASS
- CUDA
Benefits
Flexible Working
- Flexible working arrangements
Competitive Pay
- Competitive salary
Other Benefits
- Comprehensive benefits package
Career Advancement
- Professional growth opportunities
Informal Culture
- Dynamic and collaborative work environment
Find the original job posting in its most current version here. Nejo automatically captured this job from the website of Nebius and processed the information on Nejo with the help of AI for you. Despite careful analysis, some information may be incomplete or inaccurate. Please always verify all details in the original posting! Content and copyrights of the original posting belong to the advertising company.
Not a perfect match?
- FactoryPal
Senior Machine Learning Engineer(m/w/x)
Full-timeWith HomeofficeSeniorBerlin - RepRisk AG
Senior Machine Learning Engineer(m/w/x)
Full-timeWith HomeofficeSeniorBerlin - AUTO1 Group
Senior Machine Learning Platform/Ops Engineer(m/w/x)
Full-timeWith HomeofficeSeniorBerlin - Super.AI
Machine Learning Engineer(m/w/x)
Full-timeWith HomeofficeExperiencedBerlin
NENebius
Senior ML Engineer - Token Factory(m/w/x)
Berlin
Full-timeWith Home OfficeSenior
AI/ML
Data Science
Nejo AI Summary
Optimizing LLM inference performance, implementing novel speculative decoding architectures at cloud computing provider for global AI. Experience profiling GPU workloads and GPU memory hierarchy understanding required. Flexible working arrangements.
Requirements
- Understanding of machine learning foundations
- Experience profiling GPU workloads
- Understanding of GPU memory hierarchy
- Familiarity with LLM architectures
- Understanding of neural network training
- Strong software engineering skills
- Experience with deep learning frameworks
- Proficiency in CI/CD and versioning
- Strong communication and leadership abilities
- Experience with open-source inference engines
- Experience with kernel languages
- Track record of delivering products
- Experience developing large distributed systems
- Open-source projects showcasing engineering prowess
- Excellent command of English language
Tasks
- Identify LLM inference bottlenecks
- Drive production speedups
- Maximize performance for LLM architectures
- Support and optimize inference engines
- Implement novel speculative decoding architectures
- Optimize dense and MoE components
- Contribute to open-source inference engines
- Design low-precision training pipelines
- Productionize FP8 and NVFP4 inference
- Improve throughput and cost-efficiency
Work Experience
- approx. 4 - 6 years
Education
- Bachelor's degreeOR
- Master's degree
Languages
- English – Business Fluent
Tools & Technologies
- Nsight
- PyTorch profiler
- Python
- CI/CD
- vLLM
- SGLang
- TensorRT-LLM
- Triton
- Cute
- CUTLASS
- CUDA
Benefits
Flexible Working
- Flexible working arrangements
Competitive Pay
- Competitive salary
Other Benefits
- Comprehensive benefits package
Career Advancement
- Professional growth opportunities
Informal Culture
- Dynamic and collaborative work environment
Find the original job posting in its most current version here. Nejo automatically captured this job from the website of Nebius and processed the information on Nejo with the help of AI for you. Despite careful analysis, some information may be incomplete or inaccurate. Please always verify all details in the original posting! Content and copyrights of the original posting belong to the advertising company.
About the Company
Nebius
Industry
IT
Description
The company is leading a new era in cloud computing to serve the global AI economy by creating tools and resources for real-world challenges.
Not a perfect match?
- Nebius
Senior Backend Developer (Token Factory)(m/w/x)
Full-timeWith HomeofficeSeniorBerlin - FactoryPal
Senior Machine Learning Engineer(m/w/x)
Full-timeWith HomeofficeSeniorBerlin - RepRisk AG
Senior Machine Learning Engineer(m/w/x)
Full-timeWith HomeofficeSeniorBerlin - AUTO1 Group
Senior Machine Learning Platform/Ops Engineer(m/w/x)
Full-timeWith HomeofficeSeniorBerlin - Super.AI
Machine Learning Engineer(m/w/x)
Full-timeWith HomeofficeExperiencedBerlin