Radical Numerics

Radical Numerics

Member of Technical Staff, Inference

San Francisco · Staff+

Work authorization required$26k-$42kDetected 37 days ago
PythonDistributed SystemsFull-Stack DevelopmentCloud PlatformsMachine LearningNLPLLMsBioinformaticsCRISPRResearch

About the role

  • Your work will focus on delivering state-of-the-art inference performance for large-scale genome and multimodal biological models across a wide range of real-world applications, including therapeutics, diagnostics, synthetic biology, and biodefense.
  • This is a highly technical role at the intersection of AI systems, distributed computing, and model deployment.
  • Success in this role requires deep expertise in large language model inference, kernel optimization, GPU systems, and performance engineering.

Responsibilities

  • Drive end-to-end performance improvements. Identify and eliminate bottlenecks across the inference stack, from model execution and memory management to networking, scheduling, and hardware utilization.
  • Develop high-performance inference primitives. Build and optimize GPU kernels, numerical operators, and serving infrastructure to maximize throughput, latency, and efficiency on modern accelerator platforms.
  • Build scalable deployment infrastructure. Create systems for serving, monitoring, benchmarking, and operating foundation models reliably across cloud, enterprise, and secure environments.
  • Collaborate with research and platform teams. Ensure new model architectures can be efficiently deployed at scale and help translate frontier AI research into real-world impact.
  • Excellent technical communication. Ability to collaborate effectively across research, engineering, infrastructure, and scientific teams.
  • Drive end-to-end performance improvements.
  • Develop high-performance inference primitives.

Requirements

  • Expertise in large-scale AI inference systems.
  • Proven experience optimizing, deploying, and operating LLMs or other foundation models in production environments.
  • Deep understanding of GPU architectures and experience with CUDA, Triton, or equivalent technologies for building high-performance numerical software.
  • Ability to diagnose and solve bottlenecks across the full stack, including model architectures, serving systems, networking, memory management, and distributed infrastructure.
  • Strong software engineering fundamentals with proficiency in Python and modern ML frameworks such as PyTorch.

Nice to have

  • Experience with inference frameworks such as vLLM, TensorRT-LLM, SGLang, DeepSpeed, or similar systems.
  • Contributions to open-source AI infrastructure, inference frameworks, compilers, or kernel libraries.
  • Experience with distributed systems, cloud infrastructure, and large-scale GPU clusters.
  • Familiarity with biological foundation models, computational biology, genomics, or scientific AI applications.
  • Experience operating AI systems in regulated, secure, or mission-critical environments
  • Work on some of the largest and most capable open biological AI models, helping transform breakthroughs in AI research into real-world impact across therapeutics, diagnostics, synthetic biology, and biodefense.
  • Join a team that brings together expertise in distributed systems, model architecture, numerics, AI safety, and biology.
  • It also prohibits unlawful discrimination based on the perception that anyone has any of those characteristics, or is associated with a person who has or is perceived as having any of those characteristics.

Compensation

  • $26k-$42k

Company info

  • Radical Numerics http://radicalnumerics.ai is an AI research lab building general biological intelligence. Our mission is to master the code of life, and our purpose is to reduce human suffering.
  • Our team created Evo, and started the field of generative genomics. Our work was featured on the cover of Science https://www.science.org/doi/10.1126/science.ado9336, and presented by our CEO on the main stage of TED2025 https://www.youtube.com/watch?v=EnbfoFUFm2s. Evo was used to create the first AI gene therapy tool CRISPR-Cas9, and the first AI whole genome https://www.biorxiv.org/content/10.1101/2025.09.12.675911v1 from scratch. Evo 2 https://www.nature.com/articles/s41586-026-10176-5, featured in Nature, is the largest fully open source AI project across any domain.
  • Radical Numerics is bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We've redesigned the foundation model training stack to turn the world's raw scientific data (e.g. biological sequences, experiments, and physical processes), into intelligible, generative models that can expand and accelerate what humanity can understand, design, and cure.
  • The same generative breakthroughs that enable life-saving cures also lowers the barrier to creating engineered threats and AI-generated bioweapons. We believe these forces are inseparable. Radical Numerics was founded to develop both the power to design and the responsibility to defend.
  • Radical Numerics http://radicalnumerics.ai is an AI research lab building general biological intelligence.
  • Our mission is to master the code of life, and our purpose is to reduce human suffering.
  • Our team created Evo, and started the field of generative genomics.
  • Our work was featured on the cover of Science https://www.science.org/doi/10.1126/science.ado9336, and presented by our CEO on the main stage of TED2025 https://www.youtube.com/watch?v=EnbfoFUFm2s.
  • Evo was used to create the first AI gene therapy tool CRISPR-Cas9, and the first AI whole genome https://www.biorxiv.org/content/10.1101/2025.09.12.675911v1 from scratch.
  • Evo 2 https://www.nature.com/articles/s41586-026-10176-5, featured in Nature, is the largest fully open source AI project across any domain.
  • Radical Numerics is bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology.
  • We've redesigned the foundation model training stack to turn the world's raw scientific data (e.g. biological sequences, experiments, and physical processes), into intelligible, generative models that can expand and accelerate what humanity can understand, design, and cure.
  • The same generative breakthroughs that enable life-saving cures also lowers the barrier to creating engineered threats and AI-generated bioweapons.
  • We believe these forces are inseparable.

Visa & Work Authorization

  • Radical Numerics participates in E-Verify and will provide the federal government with your Form I-9 information to confirm that you are authorized to work in the U.S.
Apply directly at Radical Numerics →Create a free account for alerts like thisView Radical Numerics immigration profile

This listing is sourced directly from Radical Numerics's careers page and normalized into a canonical job model.