Behind our name: Like fire, AI holds the potential for both immense benefit and significant risk. Just as mastering fire transformed human history, we believe the safe and intentional development of AI will shape the future of our species. Our goal is to tame this new fire.
Goodfire is an AI interpretability research company focused on understanding and designing AI systems that people can trust. Our mission is to advance humanity's understanding of AI to build safe and powerful AI systems. We believe that deep research breakthroughs are necessary to make this possible.
Goodfire is a public benefit corporation headquartered in San Francisco with a team of the world’s top interpretability researchers and engineers from organizations like OpenAI and DeepMind. We’ve raised $59M from investors like Menlo, Lightspeed and Anthropic and work with customers including Arc Institute, Mayo Clinic, and Rakuten.
We’re looking for a Research Engineer to help build the systems that power cutting-edge interpretability research. You’ll play a central role in scaling and deploying tools that analyze and steer large models.
Where you might contribute:
- Interpretability mechanisms – Build tools and infra to support foundational model probing.
- Moonshots – Rapidly prototype novel interpretability systems with high-upside potential.
- Applied research & usability – Turn interpretability techniques into robust, usable features.
We'll work with you to determine the pod that best aligns with your strengths.
Key responsibilities:
- Develop robust tooling for analyzing and visualizing model internals.
- Optimize pipelines and infra for large-scale interpretability workflows.
- Partner with researchers to iterate quickly on experimental techniques.
- Help deploy interpretability tools into product and production contexts.
- Ensure system reliability, reproducibility, and performance.
- 5+ years of experience in ML infra, research engineering, or systems programming.
- Comfort working across research and engineering boundaries.
- Expertise in Python, PyTorch or Jax, and distributed systems.
- Experience deploying and maintaining ML systems at scale.
- Enthusiasm for helping AI systems become safer and more interpretable.
- Prior work on model internals, explainability, or interpretability.
- Open-source ML infra contributions.
- Startup or lab experience in fast-moving teams.
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.
What we offerThis role offers market competitive salary, equity, and competitive benefits.
The expected salary range for this position is $180,000 - $350,000 USD
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.
Top Skills
What We Do
Our mission is to advance humanity's understanding of AI by examining the inner workings of advanced AI models (or “AI Interpretability”). As a research-driven product organization, we bridge the gap between theoretical science and practical applications of interpretability.
We're building critical infrastructure that empowers developers to understand, edit, and debug AI models at scale, ensuring the creation of safer and more reliable systems.
Goodfire is a public benefit corporation headquartered in San Francisco.
