--- title: 'Research Scientist (London) at Goodfire' canonical: 'https://feeny.ai/job/research-scientist-london-goodfire-london-1t9ssxtvrbev' type: 'job' last_seen: '2026-09-15' --- # Research Scientist (London) at Goodfire - **Company:** Goodfire - **Location:** London, United Kingdom - **Posted:** 2026-08-06 - **Last confirmed live:** 2026-09-15 - **Apply:** https://job-boards.greenhouse.io/goodfire/jobs/5382137008 ## Job description ## About Goodfire Goodfire is an AI interpretability research lab. We build interpretability agents and infrastructure to understand, monitor, and align AI models. We believe that AI is the most consequential technology of our time. Yet AI models are trained by trial and error today, with limited understanding of what drives their behavior. Our goal is to advance the research and technology needed to fully understand and align AI so humanity can trust superintelligence. Goodfire is a public benefit corporation founded by researchers who helped pioneer the field of interpretability at OpenAI and Google DeepMind. We are headquartered in San Francisco and have raised over $200M from leading investors including Lightspeed, Menlo, and B Capital. ## About the role We’re looking for a Research Scientist to join our team and develop new techniques for understanding and steering large AI models. You’ll work closely with a small, mission-driven team of scientists and engineers to conduct novel research, build practical tools, and push the field forward. Where you might contribute: - Interpretability mechanisms – Foundational research on how models represent and process information. - Moonshots – High-upside bets on novel techniques that could unlock breakthroughs in model understanding. - Applied research & usability – Translating research into tools for real-world users and enterprise applications. You’ll be working closely with our team in London, who focus on mechanistic understanding of the algorithms that neural networks have learned. Key responsibilities: - Conduct original research in interpretability and related fields. - Prototype techniques to visualize and manipulate internal model structures. - Collaborate with engineering to turn research into production-ready tools. - Share your work through publications, demos, and open-source contributions. - Help define and evolve our research direction. ## What you’ll bring Required experience - PhD or equivalent experience in ML, computer science, or a quantitative science. - Deep familiarity with large models and a passion for understanding how they work. - Fluency in Python and ML frameworks such as PyTorch. - Strong writing and communication skills for explaining complex ideas. - Drive to move quickly and take ownership. ## Preferred qualifications - Experience leading research or contributing to open-source codebases. - Familiarity with interpretability, alignment, or safe model development. - Experience in startup or fast-paced lab environments. ## Our values Goodfire is looking for individuals who embody our values and share our deep commitment to making interpretability accessible. We are building a team first and foremost. Put mission and team first All we do is in service of our mission. We trust each other, deeply care about the success of the organization, and choose to put our team above ourselves. Improve constantly We are constantly looking to improve every piece of the business. We proactively critique ourselves and others in a kind and thoughtful way that translates to practical improvements in the organization. We are pragmatic and consistently implement the obvious fixes that work. Take ownership and initiative There are no bystanders here. We proactively identify problems and take full responsibility over getting a strong result. We are self-driven, own our mistakes, and feel deep responsibility over what we’re building. Action today We have a small amount of time to do something incredibly hard and meaningful. The pace and intensity of the organization is high. If we can take action today or tomorrow, we will choose to do it today. Where we work We are hiring for this position in our London, England office. We are in person 5 days a week, with one company-wide remote week per month. ## What we offer This role offers market competitive salary, equity, and competitive benefits. The expected salary range for this position is £150,000 to £300,000 GBP. Most importantly, you'll have the opportunity to join a vital mission at an important point in its trajectory — we are developing groundbreaking technology with a world-class team on the critical path to ensuring a safe and beneficial future for humanity. If you want to do your life’s work with us, even if you believe you do not meet every single requirement, apply now. ## About Goodfire ## Company Overview - **One-liner**: Goodfire is an AI interpretability research company and public benefit corporation that builds tools to understand, debug, and intentionally design neural networks. - **Entity Type**: Private (Series B, $207M total funding) - **Headquarters**: San Francisco, California, United States (Telegraph Hill office) - **Founded**: 2024 - **Founders**: Eric Ho (CEO) and Daniel Balsam (CTO) ## Core Business - **Primary industry**: AI interpretability, software development, artificial intelligence research - **Target customers**: B2B – enterprises building or deploying AI models, particularly in life sciences (Arc Institute, Mayo Clinic), robotics, and large language model applications - **Mission**: To advance humanity's understanding of AI to build safe and powerful AI systems – making AI that can be understood, debugged, and shaped like software. ## Products & Services - **[Silico for LLMs](https://www.goodfire.ai/)**: A platform that uncovers hidden representations inside neural networks, enabling users to debug hallucinations, steer model behavior, and train with less data. Uses feature-based interpretability and steering vectors. - **[Silico for Life Sciences](https://www.goodfire.ai/)**: Applies interpretability to genomic and epigenetic models (e.g., Evo 2) to discover novel biomarkers and biological insights. - **[Silico for Robotics & Vision](https://www.goodfire.ai/)**: Reverse-engineers causal mechanisms in vision and robotics models to inspect latent policy structure and improve reliability. - **Research Division**: Publishes foundational interpretability research (e.g., steering along manifolds, interpreting language model parameters, performative chain-of-thought detection). ## Market Standing - **Valuation/Market Cap**: Not disclosed (private company) - **Key Metric**: Total funding of **$207M** across three rounds: - Seed (Aug 2024): $7M led by Lightspeed Venture Partners - Series A (May 2025): $50M led by Menlo Ventures - Series B (Feb 2026): $150M led by B Capital - **Notable Investors/Partners**: Lightspeed Venture Partners, Menlo Ventures, B Capital, Anthropic; customers include Arc Institute, Mayo Clinic, and Rakuten. - **Growth Signals**: Headcount of 46 employees (+231% YoY); LinkedIn followers 8,604 (+180% YoY); expanding to a New York office; published research in Nature (Evo 2 interpretation). ## Competitive Advantages - **Deep interpretability expertise**: Team includes pioneers of sparse autoencoders, automated feature interpretation, and knowledge extraction from superhuman models – founding members of interpretability efforts at OpenAI, Google DeepMind, and academic labs. - **Platform approach**: Silico works across LLMs, life sciences, and robotics, offering a unified interface for debugging and intentional design. - **Scientific track record**: Demonstrated reduction of hallucinations by 58% at ~90x lower cost than LLM-as-judge, and discovered novel Alzheimer's biomarkers via model interpretation. - **Public benefit corporation**: Mission-driven structure reinforces focus on safe, beneficial AI development. ## Strategic Focus - **Intentional design agenda**: Moving AI development from guess-and-check to closed-loop control by using interpretability to guide training directly. - **Research-to-product pipeline**: Rapidly translating cutting-edge interpretability research into robust, usable product features for customers. - **Expanding verticals**: Life sciences and robotics are key growth areas, with partnerships at top research institutions. ## Why Work Here - **Culture**: High-intensity, fast-paced, mission-driven environment. Team values include "take action today," ownership, and kindness. All roles are in-person 5 days a week at the San Francisco (Telegraph Hill) or New York office, with one company-wide remote week per month. - **Compensation**: Competitive salary ($200,000 – $400,000 USD range for many roles), equity, and benefits. - **Team**: Work alongside world-class researchers and engineers from OpenAI, DeepMind, Stanford, and Harvard. Small team (~46 people) with high ownership and direct impact on foundational AI science. - **Perks**: Opportunity to do "life's work" on the critical path to safe AI; involvement in groundbreaking research published in top venues. ## Sources 1. [goodfire.ai](https://www.goodfire.ai/) – Company website, product descriptions, research 2. [goodfire.ai/company](https://www.goodfire.ai/company) – About page, team background 3. [goodfire.ai/careers](https://www.goodfire.ai/careers) – Careers overview 4. [greenhouse.io](http://job-boards.greenhouse.io/goodfire) – Job listings, salary ranges, location policy 5. [linkedin.com](https://www.linkedin.com/company/goodfire-ai) – Funding details, headcount, growth metrics, key executives ## Other roles at Goodfire - [Senior Counsel](https://feeny.ai/job/senior-counsel-goodfire-san-francisco-stfkkzrf9r42) — San Francisco, CA - [Director of People](https://feeny.ai/job/director-of-people-goodfire-san-francisco-7fftr5y4y1v3) — San Francisco, CA - [Forward Deployed Research Scientist](https://feeny.ai/job/forward-deployed-research-scientist-goodfire-san-francisco-a57ke1chqhpt) — San Francisco, CA - [Head of Recruiting](https://feeny.ai/job/head-of-recruiting-goodfire-san-francisco-a1tp009k7wb7) — San Francisco, CA - [Executive Assistant](https://feeny.ai/job/executive-assistant-goodfire-san-francisco-h2r7hqzef7gy) — San Francisco, CA - [Research Lead, Training](https://feeny.ai/job/research-lead-training-goodfire-san-francisco-774dyv8fr343) — San Francisco, CA - [Account Executive, High Tech](https://feeny.ai/job/account-executive-high-tech-goodfire-san-francisco-zd1gscyqeakn) — San Francisco, CA - [Product Engineer](https://feeny.ai/job/product-engineer-goodfire-san-francisco-wd8kpngkrpws) — San Francisco, CA - [GTM Recruiter](https://feeny.ai/job/gtm-recruiter-goodfire-san-francisco-xedws5v0fntt) — San Francisco, CA - [Account Executive, Life Sciences](https://feeny.ai/job/account-executive-life-sciences-goodfire-san-francisco-vbcv2mbbggg8) — San Francisco, CA