---
title: 'Member of Technical Staff, Post-Training at Radical Numerics'
canonical: 'https://feeny.ai/job/member-of-technical-staff-post-training-radical-numerics-san-francisco-e3h9ssf1mhqk'
type: 'job'
last_seen: '2026-09-14'
---

# Member of Technical Staff, Post-Training at Radical Numerics

- **Company:** Radical Numerics
- **Location:** San Francisco, CA
- **Employment:** full-time
- **Work type:** onsite
- **Posted:** 2026-03-17
- **Last confirmed live:** 2026-09-14
- **Apply:** https://jobs.ashbyhq.com/radical-numerics/93199b3d-6560-489c-8e41-b6cc48dd0568

## Job description

## About Us

[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.

## About the Role

As a Member of Technical Staff, Post-Training at Radical Numerics, you will develop the training and evaluation loops that shape biological world models after pretraining. You will work on the methods, data, and infrastructure required to improve model behavior on real scientific tasks: reasoning over long biological context, following complex objectives, making useful predictions, and interacting reliably with downstream tools and workflows. This is a hands-on role for someone who wants to both build systems and deepen understanding. You should be excited to run careful experiments, question whether the metrics reflect reality, and translate empirical findings into better recipes, datasets, and productively used models.

We believe the next generation of biological foundation models will require not only new and improved pretraining recipes, but also innovation on post-training: the work that turns a powerful base model into a system that is useful, steerable, robust, and scientifically productive. This role sits at that interface between fundamental research and practical engineering.

## What You’ll Do

- Develop and tune post-training recipes. Design and iterate on post-training stages, datasets, reward signals, and hyperparameters for biological world models. Study how choices in data mixtures, objective design, curriculum, and training schedules affect model behavior.
- Build evaluations that actually matter. Collaborate with the science team to develop and refine evaluation suites for biological reasoning, scientific usefulness, long-context behavior, robustness, and model reliability, and to identify when existing benchmarks stop being informative and should be replaced with better ones.
- Debug model behavior end-to-end. Investigate failure modes in training runs and model outputs, distinguish between signal and noise, and trace problems back to data, optimization, evaluation design, or systems issues.
- Work on preference- and feedback-driven learning. Explore methods such as preference modeling, reward modeling, synthetic feedback, or related post-training approaches that improve how models respond to scientific tasks and constraints.
- Improve data for post-training. Help define, curate, or generate high-quality post-training datasets, including expert-informed data, synthetic data, and task-specific examples grounded in biological workflows.
- Study scaling in post-training. Measure how performance changes with dataset size, recipe complexity, compute budget, and model family. Use those results to guide what we scale next and what new directions are worth exploring.
- Collaborate across research and engineering. Work closely with colleagues in training systems, architecture, and biology-facing research to ensure post-training methods are grounded in the realities of large-scale experimentation and downstream scientific use.

## What We’re Looking For

- Strong track record in ML research or engineering, especially in frontier-model training, post-training, alignment, evaluation, data quality, or related areas.
- Proficiency in building production-quality software and research infrastructure, ideally in Python and PyTorch, with comfort debugging large-scale training workflows.
- Ability to design careful experiments, interpret ambiguous results, and separate real effects from artifacts, bugs, or benchmark overfitting.
- Excellent written and verbal communication skills, especially the ability to explain technical findings clearly across research, engineering, and scientific collaborators.
- Curiosity, rigor, and a bias toward iteration: you like improving systems by repeatedly tightening the loop between hypotheses, experiments, and insight.

## Nice to Have

- Experience with RLHF, RLAIF, preference optimization, reward modeling, rejection sampling, or other post-training methods for large models.
- Experience designing or operating evaluation frameworks for model quality, reliability, safety, or scientific task performance.
- Familiarity with synthetic data generation, annotation workflows, or expert-in-the-loop data collection.
- Background in applied math, systems, computational biology, or another quantitative scientific field.
- Contributions to open-source ML systems, model tooling, or research infrastructure.

## Why Radical Numerics

- Help build the post-training stack for multimodal biological world models that could materially improve how we detect, understand, and respond to problems in health and biology.
- Work in an environment that combines distributed systems, model architecture, and numerics research with real biological applications.
- Join a collaborative culture that values rigor, creativity, and cross-disciplinary partnership across AI labs, biotechs, hospital systems, and research institutes.
- Competitive compensation, comprehensive benefits, and support for continual learning.

Radical Numerics is committed to equal employment opportunity and does not discriminate in any employment opportunities or practices based on an individual's race, color, creed, gender (including gender identity and gender expression), religion (all aspects of religious beliefs, observance or practice, including religious dress or grooming practices), marital status, registered domestic partner status, age, national origin or ancestry (including language use restrictions and possession of a driver’s license issued under California Vehicle Code section 12801.9), natural hair, physical or mental disability, political affiliation, medical condition (including cancer or a record or history of cancer, and genetic characteristics), sex (including pregnancy, childbirth, breastfeeding or related medical condition), genetic information, sexual orientation, military and veteran status or any other consideration made unlawful by federal, state, or local laws. 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.

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.

## About Radical Numerics

## Company Overview
- **One-liner**: Radical Numerics is a next-generation AI lab building general biological intelligence, developing multimodal models trained on the fabric of biology to enable discovery, design, and defense in the life sciences.
- **Entity Type**: Private (Seed stage)
- **Headquarters**: San Francisco, California, USA (with a presence in Tokyo, Japan)
- **Founded**: Not publicly available (recently announced a $50M seed round)
- **Founders**: Not publicly listed (the founding team previously trained Evo and Evo 2, the largest biological AI models trained on DNA)

## Core Business
- **Primary industry**: Artificial Intelligence / Biotechnology (AI for Biology)
- **Target customers**: B2B — partnerships with diagnostics companies, U.S. national labs, and pharmaceutical/therapeutic organizations; also serves the broader scientific community through open-source models.
- **Mission or purpose statement**: "To master the code of life and to ensure this power is used to save lives." The company is building general biological intelligence to enable faster discovery, deeper understanding, and entirely new capabilities in biology, while simultaneously building biodefense systems to safeguard against misuse.

## Products & Services
- **Evo & Evo 2**: The founding team's prior open-source generative genomics models, trained on millions of genomes across all of life. Evo was used to generate the world's first complete genome from scratch using AI (a bacteriophage). These models established the field of generative genomics.
- **Omnii**: The company's next-generation genome language model (gLM). It features a multi-hybrid architecture with a 2M-token context window, multimodality, and is the first aligned large-scale genome model. It surpasses specialized models across core genetics benchmarks, especially in noncoding and regulatory regions. Omnii is being piloted for early cancer detection (with a diagnostics partner) and for biodefense/biosurveillance (with a U.S. national lab).
- **Biodefense Platform (Omnii for Biosecurity)**: A system designed to detect "deepfake" pathogens, identify suspicious sequences, and attribute engineered function — aimed at global biological resilience against natural, synthetic, and AI-generated threats.

## Market Standing
- **Valuation/Market Cap**: Not disclosed (private company)
- **Key Metric**: $50 million seed round (announced in 2025)
- **Notable Investors/Partners**: Not publicly named in the seed round announcement. Advisors include Eric Horvitz (CSO of Microsoft), Chris Ré (Stanford), George Church (Harvard), and Andrew Weber (former Assistant Secretary of Defense for Nuclear, Chemical and Biological Defense Programs). Partners include a U.S. national lab (for Omnii biodefense pilot) and a diagnostics company (for early cancer detection).
- **Growth Signals**: Raised a $50M seed round; has a data center under construction filled with NVIDIA Blackwells; actively hiring for 11+ roles across San Francisco and Tokyo; building the next generation of biological AI models with a 2M-token context window; partnering with a U.S. national lab and a diagnostics company.

## Competitive Advantages
- **Proven Track Record**: The founding team created Evo and Evo 2, the largest open-source biological AI models, which established the field of generative genomics. Evo generated the world's first complete AI-designed genome.
- **First-Mover in Alignment for Biology**: Omnii is the first large-scale genome model to incorporate alignment methods (mid- and post-training), transforming a language model into a reliable scientific instrument.
- **Dual Mandate (Design + Defense)**: Uniquely positioned as both a design lab and a defense lab under one roof, addressing the inseparable forces of biological advancement and biosecurity.
- **World-Class Advisors**: Eric Horvitz (Microsoft CSO), Chris Ré (Stanford), George Church (Harvard), and Andrew Weber (former Assistant Secretary of Defense).
- **Technical Depth**: Team has pioneered models with one-million-token context windows and is now scaling toward one billion, with a focus on novel architectures and systems engineering for scientific data.

## Strategic Focus
- **Scaling Biological AI**: Building the infrastructure (data center with NVIDIA Blackwells) to train the most powerful biological AI models in the world.
- **Dual Application**: Simultaneously advancing human health (cancer detection, therapeutic design, variant interpretation) and biodefense (pathogen detection, biosurveillance with U.S. national labs).
- **Model Innovation**: Developing new multi-hybrid architectures, long-context windows (2M tokens and scaling to 1B), multimodality, and mechanistic interpretability tools for biology.
- **Open Science Foundation**: While building proprietary systems, the team's prior work (Evo, Evo 2) was released fully open source, establishing credibility in the scientific community.

## Why Work Here
- **Mission-Driven**: The company is tackling "the most important scientific and technological challenge of our time" — mastering the code of life to cure disease, engineer new medicines, and defend against biological threats.
- **Cutting-Edge Technical Work**: Engineers and researchers work on frontier AI challenges including distributed systems, model architecture, numerics research, long-context models, and mechanistic interpretability — all applied to biological data.
- **On-Site Culture**: The vast majority of roles (10 of 11 listed) are on-site in San Francisco, with some roles also available in Tokyo. This suggests a strong in-person collaboration culture.
- **Interdisciplinary Team**: Brings together AI researchers, systems engineers, computational biologists, and scientists from institutions including Stanford, MIT, and Google DeepMind.
- **High Ambition, Early Stage**: With a $50M seed round and a small team, new hires have the opportunity to shape the company's technical direction and infrastructure from the ground up.
- **Dual Focus on Impact and Responsibility**: The company explicitly states that "the design lab and the defense lab need to be the same entity," offering engineers a chance to work on both creation and safeguarding of powerful technology.

## Sources
1. [radicalnumerics.ai](https://www.radicalnumerics.ai/)
2. [radicalnumerics.ai/about](https://www.radicalnumerics.ai/about)
3. [radicalnumerics.ai/blog](https://www.radicalnumerics.ai/blog/radical-numerics-seed)
4. [radicalnumerics.ai/join-us](https://www.radicalnumerics.ai/join-us)
5. [jobs.ashbyhq.com](https://jobs.ashbyhq.com/radical-numerics)

## Other roles at Radical Numerics

- [Member of Technical Staff, Experimental Biology](https://feeny.ai/job/member-of-technical-staff-experimental-biology-radical-numerics-san-francisco-h454zz2rrwqj) — San Francisco, CA
- [Product Lead, Biodefense](https://feeny.ai/job/product-lead-biodefense-radical-numerics-san-francisco-3wwjkb3vw9pn) — San Francisco, CA
- [Head of Business Development](https://feeny.ai/job/head-of-business-development-radical-numerics-san-francisco-318xb336bt1w) — San Francisco, CA
- [Product Lead - Discovery](https://feeny.ai/job/product-lead-discovery-radical-numerics-san-francisco-s2b2xmpxcrkj) — San Francisco, CA
- [Product Lead - Diagnostics](https://feeny.ai/job/product-lead-diagnostics-radical-numerics-san-francisco-tdmzmz9vd98n) — San Francisco, CA
- [Applications Engineer](https://feeny.ai/job/applications-engineer-radical-numerics-san-francisco-e99grz13f2db) — San Francisco, CA
- [Member of Technical Staff, Protein Design](https://feeny.ai/job/member-of-technical-staff-protein-design-radical-numerics-san-francisco-qb0q6hcghd3c) — San Francisco, CA
- [Marketing Associate](https://feeny.ai/job/marketing-associate-radical-numerics-san-francisco-j0xem583abgd) — San Francisco, CA
- [Member of Technical Staff, ML Engineer](https://feeny.ai/job/member-of-technical-staff-ml-engineer-radical-numerics-san-francisco-mdtstmkpfgmz) — San Francisco, CA
- [Member of Technical Staff, Inference](https://feeny.ai/job/member-of-technical-staff-inference-radical-numerics-san-francisco-6dkvggf3cx25) — San Francisco, CA