Jobs at Goodfire

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 intentionally designing advanced AI systems. We believe advances in interpretability will unlock the next frontier of safe and powerful foundation models and that deep research breakthroughs are necessary to make this possible.

Everything we do is in service of that mission. We move fast, take ownership, and constantly push to improve. We believe in acting today rather than tomorrow. We care deeply about the success of the organization and put the team above ourselves.

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 $57M from investors like Menlo, Lightspeed and Anthropic and work with customers including Arc Institute, Mayo Clinic, and Rakuten.

Goodfire is pioneering mechanistic interpretability, a nascent but critical field aimed at transforming opaque AI models into transparent, steerable systems. Its flagship platform, Ember, enables direct, programmable access to a model’s internal neurons, unlocking the ability to debug, shape behavior, and extract hidden knowledge. This goes far beyond today’s input-output alignment tools, addressing the core technical bottleneck of deploying AI at scale: the inability to understand why models make decisions. The implications are enormous: safer and more reliable foundation models, domain-specific insights for scientific discovery, and improved performance across enterprise AI deployments. Early collaborations with institutions like Arc Institute demonstrate Ember’s potential to accelerate breakthroughs in fields ranging from biology to advanced reasoning models.

Goodfire’s team is its defining moat. Co-founders Eric Ho (a repeat founder with prior scaled experience) and Dan Balsam are joined by some of the most influential interpretability researchers in the world, including leaders from OpenAI and DeepMind who helped originate the field. Backing from Anthropic, Menlo Ventures, and Lightspeed reflects strong conviction from both leading AI labs and top-tier investors. By combining cutting-edge research with a commercializable platform, Goodfire is uniquely positioned to become the foundational layer of trust and control for the next generation of AI systems. As models continue to scale in power and opacity, the need for mechanistic interpretability will only grow, making Goodfire an indispensable infrastructure play in the AI ecosystem.

Written as of August 2025