What We Build
Physical AI breaks after deployment. Models drift, conditions change, and on the edge there is no cloud to catch it. Edgeble self-correcting runtime keeps deployed AI accurate on-device, without stopping inference. It is in production at Tier-1 manufacturers and hardware-agnostic across edge NPUs.
The Role
When a robot's physical embodiment drifts, actuator wear and calibration shift make the AI model degrade in ways the model itself cannot see. This role is about the open problem of coupled correction: what on-device correction looks like when the physical system and the model move together. You will work against real deployment data, study how the runtime should detect the coupling, and shape correction logic that is grounded in the system rather than just the model. The goal is to move toward publishable findings while improving a deployed runtime.
How We Work
Edgeble is agent-native. We build with agentic coding workflows daily on internal platform tooling already set up for it. You direct the agents; your judgment goes on what agents cannot do: correction logic, validation design, and what better means. If you would rather type every line yourself, this role will frustrate you, self-select accordingly.
You
Robotics, controls, or ML background with strong fit for final-year or masters students from robotics labs. You should be comfortable with real deployment data, observability, and iterative experimentation. Experience across embedded systems, controls, simulation, or field robotics is useful, especially where model performance depends on the physical platform.
Why Here
Own a defined layer of a production, patent-pending runtime at the moment it scales. Early-team equity, direct work with a founder with 19 years of experience across silicon, embedded systems, Edge AI, Linux kernel/U-Boot maintenance, and physical systems, in the working style most teams are still debating.