Member of Technical Staff, Biosecurity

Location: SF Bay Area
Type: Full-time

About Radical Numerics

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast biological sequence, structure, and image datasets so that biological world models become a reality. Our team introduced hybrid architectures that unlocked million-token context windows, enabling work toward AI-designed whole genomes and real gene-editing tools.

We believe biology will be the most impactful and consequential application of AI—and that advancing capabilities must go hand-in-hand with advancing safety and biosecurity. The same systems that design biology must also help defend against it. This role is focused on building and deploying the technical systems that make biosecurity real.

About the Role

As a Member of Technical Staff, Biosecurity at Radical Numerics, you will lead the design, evaluation, and deployment of biosecurity systems for biological foundation models. You will build evaluation frameworks, define safety architecture, and work with government and external partners to translate technical capabilities into real-world biosecurity infrastructure.

This role blends research and engineering. You should be excited to move fluidly between technical depth and external engagement: understanding model behavior, building red-teaming and evaluation pipelines, designing system-level safeguards, and working with stakeholders to deploy biosecurity systems at scale.

What You'll Do

• Design and run biosecurity evaluations. Develop evaluation frameworks for biological foundation models covering sequence generation risk, synthesis screening evasion, and capability assessment across genomics, proteins, and multimodal systems. Build red-teaming pipelines and define benchmarks that measure real-world risk and misuse potential.
• Work directly with models and data. Prototype pipelines for pathogen detection, sequence classification, anomaly detection, and risk scoring of biological sequences or designs. Collaborate with research teams to understand model behavior, identify dangerous capabilities early, and inform model design with safety constraints.
• Define safety architecture. Help design system-level safeguards including access controls, gating, monitoring, human-in-the-loop review, and deployment constraints for sensitive capabilities. Contribute to internal safety standards and release policies.
• Bridge to real-world biosecurity systems. Translate technical capabilities into deployable systems such as biosurveillance platforms, sequence screening tools, and rapid detection and response pipelines. Work with government and partners to align systems with real-world workflows.
• Drive partnerships and external engagement. Engage with government agencies, help shape joint technical programs and pilots, and communicate model capabilities, risks, and mitigations clearly to stakeholders.
• Identify new opportunities. Discover product and platform opportunities in biosecurity, help define Radical Numerics' role in global biological risk infrastructure, and operate with high ownership in a fast-moving, ambiguous environment.

What We're Looking For

• Strong technical background in at least one of: machine learning and AI systems (especially large models), computational biology and bioinformatics, or biosecurity and biodefense with technical depth.
• Ability to reason concretely about what biological AI systems can and cannot do, how those capabilities translate into real-world risks, and how to measure and mitigate those risks.
• Experience building or working with ML systems, or strong computational biology experience.
• Ability to design evaluations, benchmarks, or experimental frameworks for biological data, including genomic sequences, pathogens, protein data, or multi-omics.
• Strong intuition for failure modes, adversarial behavior, and misuse risks, with the ability to translate ambiguous risks into concrete technical work.
• High agency: defines problems, runs with them, and ships.
• Excellent written and verbal communication skills, especially the ability to engage credibly with government, labs, and policy stakeholders and translate technical systems into clear narratives.

Nice to Have

• Experience with pathogen genomics, biosurveillance, or DNA synthesis screening.
• Background in AI safety, red-teaming, or model evaluations.
• Familiarity with hybrid systems such as BLAST + ML or retrieval + generation pipelines.
• Experience with models like Evo, ESM, AlphaFold, or genomic foundation models.
• Background in biodefense, intelligence, or global health security.
• Existing network across government, national labs, or global health organizations.

Why Radical Numerics

• Help build the multimodal biological world models needed for rapid detection, response, and countermeasures across global health.
• Work directly on frontier biological AI systems and define how they are evaluated, controlled, and deployed.
• Help shape global infrastructure for biological risk detection and response.

Member of Technical Staff, AI Bio

Location: SF Bay Area
Type: Full-time

About Radical Numerics

Radical Numerics is an AI lab bringing the rigor of distributed systems, bioinformatics, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast multimodal biological datasets so that biological world models become a reality. Our team introduced the first hybrid architectures that unlocked million-token context windows, enabling the first AI-designed whole genomes and real gene-editing tools.

About the Role

We are seeking research scientists and engineers working at the intersection of machine learning and biological modeling to develop frontier AI architectures for biological problems.

In this role, you will extend and adapt large model backbones—such as sequence and multimodal foundation models—to enable tasks across genomics, protein biology, and cellular systems. This includes designing post-training pipelines, domain adaptation strategies, and evaluation frameworks that enable state-of-the-art  ML frameworks  to reason over biological data.  You likely know the inner workings of frontier bio models such as AlphaFold, AlphaGenome, ESM, Evo, and thought about ways to improve, evaluate or apply them in novel ways.

You will collaborate with computational biologists to systems architecture researchers to translate advances in large-scale machine learning into capabilities for modeling biological systems, ranging from genome interpretation and regulatory modeling to multimodal cellular prediction and biological design.

What You'll Do

• Adapt frontier AI models to biological tasks through fine-tuning, post-training, adapters, and architectural modifications.
• Design and run experiments applying large models to problems in genomics, regulatory biology, protein biology, or cellular systems.
• Develop evaluation pipelines and benchmarks for biological tasks such as variant interpretation, gene regulation modeling, protein function prediction, and multimodal cellular modeling — and drive these capabilities toward grounded downstream biological impact.
• Design biologically meaningful data representations and modeling schemes across sequence, molecular, and multimodal data modalities.
• Analyze model behavior and run ablations to understand model reasoning and failure modes in biological contexts.
• Explore modern mechanistic interpretability pipelines and methods for biological discovery.
• Collaborate with model architecture teams to integrate biological capabilities into next-generation foundation models.
• Prototype new approaches for biological prediction and design using foundation models.

What We're Looking For

• Strong background and intuition in machine learning and deep learning across large-scale generative architectures, from autoregressive LLMs to diffusion models. 
• Experience adapting large models to new domains through fine-tuning, post-training, adapters, or architecture modifications.
• Experience applying ML models to biological data and challenging prediction tasks.
• Familiarity with molecular biology and biological data modalities, particularly genomics, gene regulation, protein biology, or cellular systems.
• Ability to design evaluation tasks and benchmarks that measure biological model capability beyond simple accuracy metrics, with a critical eye toward aligning computational outputs with actionable downstream applications.
• Strong Python and ML tooling experience (PyTorch or JAX, experiment management, distributed training).
• Ability to interpret biological datasets and translate biological questions into machine learning experiments.
• Mid-to-senior level experience building and deploying ML systems in research or production environments.

Nice to Have

• Experience with genomic or molecular sequence models (e.g., Evo, HyenaDNA, AlphaFold-style models, AlphaGenome-style tasks, virtual cell models).
• Background in ML for structural biology, or (bio)chemistry.
• Familiarity with multimodal biological modeling, including transcriptomics, epigenomics, chromatin accessibility, or spatial biology.
• Experience building robust evaluation suites for large AI systems.
• Experience scaling ML experiments across large GPU clusters.
• Research publications in ML for biology, chemistry, or related areas.

Why Radical Numerics

• We believe biology is the most impactful and consequential application of AI.  
• Join peers that are mission driven, and dedicated to creating radically innovative tech that will change the world and human health for the better.
• Work on frontier AI systems in a collaborative culture that values rigor, creativity, and cross-disciplinary partnership across AI labs, biotechs, hospital systems, and national research institutes.