AI​/ML Engineer; Member Technical Staff

Member of the Technical Staff - AI/ML Engineer

About Transfyr

Transfyr is building physical AI for science.

Why is it that a professional athlete has dramatically more information about every play they make than a scientist has about the cause of any experimental failure? At Transfyr, we are building the infrastructure to make real-world scientific work legible, transferable, and reproducible.

Modern science is capable of extraordinary outcomes, but much of the most important insights never become explicit: how experiments are actually executed, protocols drift, how experts make gametime decisions on the fly, why experiments fail on Tuesdays. This tacit knowledge is rarely captured, making it difficult to reliably reproduce results, much less hand off protocols to new team members or collaborators.

We believe our systematic failure to capture tacit knowledge is holding back the entire industry.

We’re building systems that operate directly in real laboratory environments to elucidate, capture, and interpret this missing information. Our platform records and analyzes multimodal data about how scientific work is performed and turns it into durable, operational knowledge. In doing so, we are also building the world’s largest commercial dataset on real-world scientific execution.

This foundation is critical not only for driving elite human performance today, but for enabling meaningful automation tomorrow. Physical AI systems cannot learn from outcomes alone; they require rich, grounded records of how work is actually done in the real world.

Want to learn more? You can read some of our writings here.

AI/ML engineers at Transfyr build the learning systems that turn raw observations of scientific work into usable insight, feedback, and automation.

You will work on end-to-end ML systems that learn from messy, real-world data captured in active laboratory environments. This is not leader board-driven modeling or offline benchmark work. Your models must contend with partial observability, execution noise, changing protocols, and ambiguous outcomes and still produce signal that scientists and downstream systems can trust.

The role demands strong ML fundamentals, solid software engineering judgment, and high agency. You will work closely with perception engineers, software engineers, and scientists to ensure models are grounded in reality and tightly integrated into real workflows. We’re tackling frontier-hard AI problems and applying those models to frontier science.

We’re building a team, and we have needs across levels, from hands-on builders early in their careers to senior engineers who enjoy shaping learning architectures and technical direction.

This role is in-person in Cambridge, MA (other locations may open in the future, feel free to reach out even if Boston is not currently an option for you).

What you’ll accomplish with us:

• Learn from Messy Reality:
  Build ML systems that learn from real-world scientific execution data where feedback is delayed, labels are incomplete, and outcomes are confounded by how work was actually done.

• Fuse the World:
  Collaborate with perception engineers to design multimodal learning pipelines that combine vision, audio, sensor data, metadata, and outcomes into coherent representations of scientific workflows.

• Solve Credit Assignment:
  Develop models that can reason about why an experiment succeeded or failed when intent, execution, environment, and outcome are tightly entangled.

• Know When the Model Is Unsure:
  Build systems that surface model confidence / uncertainty, enabling scientists to understand when to trust a recommendation and when to intervene.

• Close the Loop:
  Integrate models into real workflows where outputs influence both human decisions and robotic actions, and model behavior must remain robust as protocols, operators, and environments change.

• Generalize, Don’t Memorize:
  Ensure models learn transferable structure rather than lab- or site-specific artifacts, enabling insights to carry across experiments, teams, and geographies.

• Lay the Groundwork for Automation:
  Enable future physical AI systems by ensuring models learn from execution-level data, not just…