Perception Engineer; Member Technical Staff

Member of the Technical Staff - Perception Engineer

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.

Perception engineers at Transfyr build the systems that allow our platform to see and understand real‑world scientific work as it actually happens. You will design and deploy perception systems that operate in active laboratory environments, interpreting human actions, object interactions, instruments, and automation hardware under real‑world conditions. This is not offline benchmarking on clean datasets; your work must function in messy, changing environments with imperfect lighting, occlusions, evolving protocols, and long‑tail edge cases.

The role demands strong perception fundamentals, practical engineering judgment, and high agency. You will work closely with scientists and operators, observe failure modes firsthand, and iterate until systems are robust enough to be trusted as part of critical scientific workflows.

We’re building a team, and we have needs across levels:

• Hands‑on builders early in their careers who are excited to build and ship real systems quickly
• Senior engineers who enjoy shaping system boundaries, abstractions, and long‑term 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).

• Capture the Unspoken: Design perception systems that make real‑world scientific execution legible, translating physical actions and system state into structured, reusable data
• Give Our AI Models “Sight”: Build and deploy computer vision systems that operate reliably in live laboratory environments, tracking people, objects, instruments, and automation under real‑world variability
• Build the Pipeline: Develop multimodal perception pipelines that integrate video with audio, sensor data, metadata, and experimental context, in close partnership with software and AI/ML engineers
• The Real World Is Right (Your Model Is Incomplete): Work directly alongside scientists and operators in our Cambridge‑based laboratory and at customer sites, observing failure modes firsthand and iterating until systems are robust to changing conditions (lighting, layouts, equipment, etc.)
• Scale the Science: Enable transferable science and future automation by building a physical AI layer that supports workflows generalizing across labs, teams, and geographies. Allow scientists to focus on exploration rather than bookkeeping by enabling truly passive information capture
• Enable the Robot Future: Enable generalizable automation in scientific settings by building a robust physical AI layer…