About the role
Albert already runs an advanced agentic harness in production, with fully agentic loops behind our chat experiences. You will shape where it goes next: agents that work inside every surface of Albert OS rather than a chat window, act proactively on what they see in the data model, carry goals across sessions, and run as each partner organization's own specialized scientific intelligence. You will be the most senior hands-on builder on the harness and a thinking partner to Albert's engineering and product leaders on how agentic reasoning should work across the platform. You'll report to the Director of Agentic AI. In 12 months, success looks like a harness that has moved beyond the chat window and become the runtime for organization-specific scientific intelligence, evaluated against real scientific tasks and trusted enough that partners let agents act, not just suggest.
What you'll do
- Define Albert's approach to agentic reasoning and set the technical direction of the harness, from orchestration and tool use to memory, planning, and evaluation
- Extend the harness from chat-based agents to agents that operate inside the core surfaces of Albert OS, partnering with the Director of Engineering, Core Product on the experiences that run on it
- Build the reasoning capabilities that let agents work over Albert's three-layer data model, partnering with the Knowledge Architect on how scientific intent and reasoning are represented
- Design how the harness becomes the runtime for each partner organization's own specialized scientific intelligence, learning from that organization's research and reasoning history
- Make agent behavior observable and measurable through tracing and evaluation against real scientific tasks, and use that to drive reliability at the level partners need to trust agents that act
- Stay at the frontier of what model providers and agentic frameworks make possible, and decide what Albert adopts, builds, or ignores
You will have
- You have built and operated production agent systems at scale, and have carried one past its first version through the problems that only show up in real use
- You have deep experience building on frontier model providers and know where each one breaks
- You have hands-on experience with agentic frameworks such as LangGraph or equivalent, and strong opinions about when to use one and when not to
- You have used tracing and evaluation systems such as Braintrust to make agent behavior measurable, and you treat evals as the foundation of reliability rather than an afterthought
- You think in systems and can define an approach that other engineers build on, then stay close enough to the code to know when it is wrong
- You care about science, and the idea of chemists and AI reasoning together in the open is the reason you want this job rather than a nice side effect
If you are passionate about changing the world one molecule at a time and thrive in a fast-paced, mission-driven environment, we want to hear from you.
Why Albert?
We have a huge impact. Albert is a growing team with a big reach. Our Platform facilitates the invention of materials for tens of thousands of companies and hundreds of thousands of applications - from coatings used on rockets to adhesives used in electric vehicles to 3D printed medical devices. We love distributed teams. Albert’s home-base is in the California Bay Area, but we have multiple offices and employees sprinkled around the globe. In fact, over 50% of our employees work outside of California! An international remote culture is in our DNA. We care about you. Albert works hard to create a positive environment for our employees, and we think your life outside of work is important too. We work hard and we play hard. We value diversity. Growing and maintaining our inclusive and diverse team matters to us. We are committed to being a company where our employees feel comfortable bringing their authentic selves to work and have the ability to be successful -- every day. We’re always looking for humble, sharp, and creative folks to join the Albert team. If you think you might be a fit please apply!
We help chemists change the world by building technology that understands how they work. As chemists ourselves, we know what it's like when software doesn't work the way you do, stuck with systems built by people who never spent a day at the bench. That's why we created Albert OS, the first AI-native operating system for materials science, designed to remove every obstacle between curiosity and discovery. Today we are taking that further. We are building the system where chemists and AI reason about science together, and where every chemical company can build its own frontier intelligence on top of its own research.
We are looking for somebody who has taken an agent system past its first version and knows exactly what breaks at the second. A Senior Staff AI Engineer to join our AI and ML team and define what an agentically driven platform means at Albert. This role owns the technical direction of the agentic harness at the center of Albert OS, the orchestration, tool use, memory, and reasoning layer that lets agents operate over Albert's model of scientific knowledge.