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 multimo