Member of Technical Staff, Infrastructure and Training Systems
Hybrid (SF Bay Area or Tokyo, Japan)Full-timePosted 7mo ago
About the role
Member of Technical Staff focused on designing and building large-scale model training infrastructure, distributed training systems, performance optimization, reusable internal frameworks, and tooling to accelerate research and deployment for Radical Numerics’ biological world models.
Responsibilities
- Design and scale distributed training systems. Build and optimize distributed training infrastructure for large-scale biological world models across large distributed compute systems, with a focus on performance, stability, and scalability.
- Maximize throughput and hardware efficiency. Develop performance optimizations across the stack, including communication patterns, memory efficiency, custom kernels, compilation paths, and systems instrumentation, to ensure training compute is used effectively.
- Build reusable training frameworks. Develop internal libraries, abstractions, and workflows that improve reproducibility, reliability, and scalability across new model architectures and training recipes.
- Improve reliability under rapid iteration. Establish standards and mechanisms for robustness, maintainability, debugging, and safe deployment of fast-moving research infrastructure. That includes fault tolerance, checkpointing, monitoring, experiment hygiene, and incident analysis.
- Collaborate across research and engineering. Partner closely with model researchers, training scientists, and data/infrastructure engineers to identify bottlenecks, unblock experiments, and design systems that support new scientific directions rather than constrain them.
- Support new architectures and training paradigms. Adapt infrastructure to the needs of multimodal models, long-context training, and evolving model architectures, so the systems stack remains a research multiplier as model requirements change.
Qualifications
- Strong engineering track record in distributed systems, high-performance ML infrastructure, training systems, or closely related areas.
- Proficiency in building performant, maintainable software in Python, PyTorch, Triton, CUDA, and C++.
- Strong understanding of modern deep learning frameworks and their systems internals.
- Ability to debug complex, multi-layered systems involving distributed training, memory/performance regressions, and reliability issues in large codebases.
- Comfort working in a highly collaborative environment with researchers, engineers, and domain experts, with a bias toward initiative and execution.
- Excellent written and verbal communication skills bridging technical and scientific domains.
Skills
Required:Distributed training systemsPerformance optimizationReusable training frameworksReliability and fault toleranceCollaboration with researchers/engineersAdaptability to new architectures
Last updated May 28, 2026. Interested? Apply on the company site.
About Radical Numerics
Next-gen AI lab for recursive self-improvement
Radical Numerics - Next-gen AI lab for recursive self-improvement
AIAI labrecursive self-improvement
More open roles at Radical Numerics
- Product Manager5mo agoHybrid (San Francisco, CA)
- Senior Engineering Manager5mo agoHybrid (SF Bay Area or Tokyo, Japan)
- Member of Technical Staff, Statistical Genetics5mo agoHybrid (SF Bay Area)
- Chief of Staff5mo agoHybrid (San Francisco Bay Area)
- Member of Technical Staff, Backend Engineering7mo agoHybrid (SF Bay Area), Hybrid (Tokyo, JP) · Engineering