×
Goodfire
AI Interpretability
Last verified August 18, 2026 · Updated daily
What Goodfire is building
Every neural network in existence today is, at its core, a black box. You put data in. You get output out. What happens in between – the billions of mathematical operations that transform a question into an answer, a prompt into a policy decision, a scan into a cancer diagnosis – is functionally invisible, even to the researchers who built it. The standard engineering response to this has been to treat it as an acceptable limitation: run more tests, add more safeguards, fine–tune on better data, and hope the outputs stay within acceptable bounds. That approach, naturally, is breaking down. Goodfire's thesis is that this opacity is not a fundamental property of neural networks but an engineering gap that can be closed. The science they're built on is called mechanistic interpretability: the practice of reverse–engineering neural networks to understand what is actually happening inside them, at the level of individual neurons, circuits, and features. The breakthrough that made this commercially viable is the Sparse Autoencoder (SAE): a technique for decomposing the tangled, overlapping activations of neural network neurons into individual, human–readable concepts. Goodfire's product, Ember, is the first hosted API that gives developers programmatic access to this capability at scale, i.e., developers can directly access and influence an AI model's internal workings to understand, debug, and safely steer its behavior. It ships as an API wrapper around large language models, currently supporting Llama 3 and other open models, that lets engineers inspect which internal features are activating during a model's reasoning, intervene on those features directly, and measure the precise behavioural effect of each intervention. The company has already demonstrated several real applications: cutting hallucinations in a large language model by nearly half by directly suppressing the internal features associated with confabulation; identifying a novel class of Alzheimer's biomarkers by reverse–engineering an epigenetic foundation model built by Prima Mente – the first major scientific finding obtained by interpreting a foundation model's internals rather than just its outputs; and improving safety benchmark scores for enterprise customers including Rakuten, Apollo Research, and Haize Labs. Their Series B funding, announced February 5, 2026 (less than 18 months after founding) will be used to build what they call a 'model design environment': a full platform for understanding, debugging, and intentionally designing AI models from the inside out. The phrase Eric Ho uses to describe the ambition: moving from growing AI 'like a wild tree' to shaping it 'like bonsai.' MIT Technology Review named mechanistic interpretability one of the 10 Breakthrough Technologies of 2026, and Goodfire is the company most directly commercialising that breakthrough.
Why this matters
The history of engineering is a history of fields that were transformed when practitioners stopped treating their medium as a black box and started understanding it from first principles. Steam engineers built more powerful engines for decades before thermodynamics gave them the science to understand why steam behaved the way it did and how to design engines rather than just iterate on them. Geneticists bred crops and mapped hereditary traits for a century before understanding DNA and once they understood DNA, the entire discipline of bioengineering became possible. Eric Ho makes this analogy explicitly and it is not rhetorical flourish: it is the actual structure of what is happening in AI right now. The black–box approach to AI development of training large models on vast data, evaluating outputs, adjusting training, repeat, has produced remarkable results and will continue to do so. But it is fundamentally a trial–and–error process applied to a system no one fully understands. The consequences of that opacity are becoming acute in three specific ways that are driving commercial demand for interpretability tools. First, enterprise deployment risk: 47% of organisations deploying AI in 2025 reported at least one negative consequence from that deployment, and the primary reason cited is unpredictable model behaviour that could not be diagnosed or fixed. When an AI model produces a harmful output, biased decision, or compliance violation, the current tools for diagnosing why it happened are rudimentary – the equivalent of trying to debug software by only looking at the program's final output. Ember gives enterprises a structured way to find the specific internal mechanism responsible and intervene on it directly. Second, regulatory pressure: the EU AI Act, which activates its highest–risk provisions in August 2026, requires that AI systems making consequential decisions — in credit, healthcare, hiring, law enforcement — be auditable. The current state of AI does not meet this requirement. Goodfire's interpretability layer is one of the few technically credible paths to AI systems that can be audited at the mechanistic level, not just evaluated on benchmarks. Third, and most consequentially in the long run: as AI models surpass human understanding in specific scientific domains – protein folding, drug discovery, materials science, genomics – the models themselves contain knowledge that cannot be extracted through normal interfaces. Asking an AI what it knows about Alzheimer's biomarkers only surfaces what it can articulate in language. Reverse–engineering what it has actually learned, for example, the internal representations it uses to make predictions that no human has thought of, extracts knowledge that is genuinely novel. Goodfire has done this once already, with the Alzheimer's biomarker discovery. If the technique generalises, the downstream implications for medicine and science are extraordinary.
Open roles at Goodfire
5 positions we're tracking. Roles are re-checked daily and removed when filled.
Interpretability Researchers
First seen 5 months ago
ML Engineers
First seen 5 months ago
Research Engineers
First seen 5 months ago
Applied Scientists
First seen 5 months ago
Enterprise Partnership leads
First seen 5 months ago
Know when Goodfire is hiring before anyone else
A role stays uncontested for about four days. Here's the window — and where we put you in it.
From $9/month, cancel any time.
Watching Goodfire
0 applicantsRole spotted & verified
1You get the alert
1You've applied
~8Hits the job boards
250+Hiring outlook
Raised $150M less than a year after Series A, scaling research team
Working at Goodfire
Goodfire is AI Interpretability, founded in and now people. What this means for you: opportunity to shape your role based on the company stage.
San Francisco is where most Goodfire positions are located.
How to actually get hired at Goodfire
Why applying the normal way doesn't work
Goodfire uses an ATS, but referrals still come first. Cold applications aren't ignored — they're just behind referrals, sourced candidates, and recruiter picks.
Who to contact at Goodfire
We're still mapping Goodfire's hiring process. At this size ( people, AI), the hiring manager typically decides, but we haven't confirmed it yet.
What Goodfire screens for
The open–source entry point: Goodfire has open–sourced its Sparse Autoencoder interpreters. The best non–application path into the company is to fork the repo, run experiments on your own models, and share your findings publicly on the Alignment Forum, arXiv, or X. This is exactly how Goodfire's own team built their reputations, and Eric monitors this community directly. A well–written public post that uses Goodfire's tools and cites their papers is worth more than a cold email. The community shortcut: The mechanistic interpretability research community is small and tight–knit. The key gathering point is the MATS (ML Alignment Theory Scholars) programme – several Goodfire researchers went through it or supervise it. Attending MATS, applying for ARENA (the AI safety training programme), or engaging with Neel Nanda's TransformerLens community puts you in direct contact with the researchers who hired the Goodfire team. The B Capital signal: The Series B was led by B Capital with Eric Schmidt and Salesforce Ventures joining. Salesforce Ventures specifically signals that enterprise CRM and workflow AI is a target market for Ember. If you have Salesforce ecosystem experience combined with any ML background, that combination is unusual and directly relevant to an underserved hiring need. The employee to find: Search LinkedIn for 'Goodfire' and look specifically for researchers who transitioned from Anthropic's interpretability team or from MATS cohorts. These individuals are the natural referral network, engaging with their published work before requesting a referral is the warmest path in.
Tailor your CV to the specific Goodfire role rather than sending a general one. Applications that mirror the language of the job description clear automated filters at a materially higher rate.
Don't make these mistakes
Positioning yourself as a generalist ML engineer. They want deep expertise in interpretability or adjacent areas. This is a research lab, not a product company.
Mistakes that kill Goodfire applications
Don't send the same CV you sent everywhere else. At people it's obvious, and it's the fastest rejection there is.
Lead with their problem, not your ambition. Goodfire is focused on The history of engineering is a history of fields that were transformed when practitioners stopped treating their medium as a black box and started understanding it from first principles — show you understand that.
Most AI applications get ghosted. A day-five follow-up can double your response rate.
Applying to Goodfire? Get the contact, not the form.
The Goodfire interview process
4 stages · 14 days typical · take-home: yes · modelled from similar companies
We don't yet have verified candidate reports for Goodfire. What follows is the typical process for a -person AI company — treat it as a model, not confirmed detail.
Interview stages
Recruiter Screen
Phone or video · 30 min
Basic qualification and logistics
Recruiter or HR
Hiring Manager Interview
Video call · 45 min
Role fit and experience deep-dive
Hiring manager
Technical/Functional Round
Video call · 60 min
Skills assessment and problem-solving
Team members
Final Round
In-person or video · 60 min
Culture fit and cross-functional alignment
Senior leadership
Goodfire take-home assignment
Goodfire includes a take-home exercise in their interview process. For AI roles, this typically involves a practical problem that takes 2-4 hours. Focus on clean, working code over premature optimization. They're evaluating how you think and communicate, not just the solution.
Goodfire interview timeline
Goodfire runs about days from first contact to offer. The median for AI companies at people is 14 days, so Goodfire is about average than most.
Interviewed at Goodfire?
Tell us how it went — stages, questions, timeline. Takes 90 seconds and it's how this page stays accurate for the next person.
Submit your Goodfire interview experience →Goodfire jobs, frequently asked questions
How many jobs does Goodfire have open?
We're tracking 5 active openings at Goodfire (verified February 2025).
Does Goodfire hire remotely?
Currently, Goodfire only has in-office roles in San Francisco.
What roles is Goodfire hiring for?
Goodfire is hiring across Other, Engineering, Data. The most recent opening is Interpretability Researchers.
How do I apply for a job at Goodfire?
Click through to apply, or see our detailed guide on landing a job at Goodfire.
Does Goodfire respond to cold emails?
We haven't verified response rates at Goodfire yet.
Who is the hiring manager at Goodfire?
At this size, hiring is usually run by the hiring manager.
How competitive is it to get hired at Goodfire?
Roles at -person AI companies typically draw 100-250 applicants in the first two weeks. Applying inside 72 hours of a posting going live is the single biggest lever you control.
How many rounds is the Goodfire interview?
4 stages: Recruiter Screen, Hiring Manager Interview, Technical/Functional Round, Final Round.
Is the Goodfire interview hard?
The interview emphasizes technical depth and system design over abstract problems. Hardest stage: Technical Interview.
Does Goodfire give a take-home task?
Yes, Goodfire includes a take-home assignment.
How long does Goodfire take to get back to you?
Around 14 days across the full process.
What should I prepare for the Goodfire interview?
Study technical depth and system design. At this size (), they care about self-sufficiency over textbook knowledge.
Where is Goodfire based?
Goodfire is headquartered in San Francisco.
Get Goodfire roles before they're posted
A role stays uncontested for about four days. Here's the window — and where we put you in it.
From $9/month, cancel any time.
Watching Goodfire
0 applicantsRole spotted & verified
1You get the alert
1You've applied
~8Hits the job boards
250+