Summary:
Location: Amsterdam
Duration: 3-6 months
Start date: June 2026
Compensation: Paid
Eligibility: Current University student (Computer Science or related field), Recent Graduate or Early Career specialist
Work authorization: Permitted to work in the job’s location
About the role
Biological AI models (protein folding, protein design, and large foundation models) are powerful but heavy and expensive to run. This project focuses on making them faster and more efficient at inference time without significantly hurting biological quality.
You will work on profiling bottlenecks, applying model compression and architectural optimizations, and building efficient inference pipelines. The goal is to make these models practical for real-world research and production use.
Your responsibilities will include:
- Profile inference bottlenecks in selected biological models
- Implement and test optimization techniques (quantization, pruning, distillation)
- Explore efficient attention and architecture-level improvements
- Build and benchmark optimized inference pipelines
- Evaluate speed, memory, and accuracy trade-offs
- Write clean, well-documented experimental code
- Share results and practical deployment recommendations
We expect you to have:
- Enrollment in or completion of a degree in computer science, AI, or a related field
- Strong knowledge of computer science and machine learning fundamentals
- Experience with Python and familiarity with deep learning frameworks
- Ability to write clean, efficient code
- Strong problem-solving skills and a willingness to learn quickly
- Interest in life sciences
Nice to have:
- Familiarity with large language models and transformer architectures
- Experience profiling GPU workloads and optimizing deep learning systems
- Experience with model compression techniques (quantization, pruning, distillation)
- Experience working with large-scale models or distributed inference
- Contributions to open-source ML projects
What we offer:
- Competitive salary and comprehensive benefits package
- Mentorship from experienced AI, ML, and cloud infrastructure professionals
- Hands-on experience with real customer workloads and production systems
- Opportunities for professional growth within Nebius
- A dynamic and collaborative work environment that values initiative and innovation
- Opportunity to be considered for a full-time role after the Early Talent Program
We’re growing and expanding our products every day. If you’re up to the challenge and are excited about AI and ML as much as we are, join us!