Rohan Gangakhedkar.

Senior R&D Engineer  ·  Eyebot  ·  Boston

Bringing machine
vision into focus.

I build the perception and calibration systems inside eye-scanning hardware — stereo depth, infrared photoretinoscopy, and the unglamorous measurement work that turns a camera into an instrument a clinic can trust.

Work

01 — Professional
Nov 2025 — Present Boston, USA

Senior R&D Engineer

Eyebot

  • Designed and shipped the eyescanner's pupillary distance measurement system from scratch on stereo-depth cameras, with an ML calibration model mapping camera geometry to a pixel-to-millimetre scale — 0.57 mm mean error, a ≈3× accuracy improvement, deployed fleet-wide.
  • Developed the facetracking algorithm — real-time face detection and 3D localization on Luxonis OAK-D stereo cameras — driving closed-loop linear and angular motor control to align the optics to a user's eyes, with an open-loop feed-forward stage when camera feedback drops out.
  • Built the world's fastest binocular lensometer from scratch, including the core lens border-detection and progressive-lens detection algorithms, extracting SPH, CYL, AXIS and PD from a user's glasses.
  • Developed the infrared photoretinoscopy pipeline — pupil detection, slope extraction, real-time prescription — and a diopter calibration curve that cut prescription error ≈30% below the prior production system.
  • Created the internal factory test suite through which all kiosk calibration and bring-up is performed, now standard across manufacturing; owned the full release lifecycle.
Mar 2024 — Nov 2025 Boston, USA

R&D Engineer

Eyebot

  • Optimized lens-scanning software in Python for a significant increase in processing speed, and implemented calibration routines for the eye- and lens-scanning hardware.
  • Designed and fabricated mechanical calibration "eyes" via rapid prototyping, and built a reusable repeatability-testing framework used to validate the eye- and lens-scanning fleet.
Sep 2023 — Mar 2024 Boston, USA

R&D Engineering Intern

Eyebot

  • Performed data analysis on eye data from clinic operations to identify and correct errors, improving the accuracy and reliability of Eyebot's equipment.
2022 — 2023 New York, USA

Robotics Research Assistant

New York University · AI4CE Lab

  • Designed and integrated a PCB with an NVIDIA Jetson to unify the systems of a mobile 3D-printing robot.
  • Managed the design and creation of a multi-DOF robotic arm, enabling optimized control for 3D printing.
  • Built a simulation environment in Gazebo, Python and ROS to validate the robot's systems.

About

02 — Background

I work where cameras stop being cameras and start being instruments. That means stereo geometry, infrared optics, and calibration — the part of computer vision where a number has to be right, not merely plausible, because somebody is going to wear the answer on their face.

At Eyebot I own the measurement stack of a self-service eye exam: finding a face in 3D and driving motors to meet it, reading a prescription out of infrared reflections, and pulling SPH, CYL and AXIS out of a pair of glasses. Most of the work is proving the thing is accurate — mechanical calibration eyes, repeatability rigs, clinical studies, and the factory tests that let a kiosk leave the building.

Before that: a master's at NYU in mechatronics and robotics, research on mobile 3D-printing robots at the AI4CE Lab, and a mechatronics degree in Auckland. The projects below are from that period — controls, perception and a fair amount of building things that move.

Now
Senior R&D Engineer, Eyebot — Boston, MA
Education
MS Mechatronics & Robotics, NYU — GPA 3.97, 2023
BE (Hons) Mechatronics, Auckland — First Class Honours, 2020
Languages
Python
Vision & ML
OpenCV, PyTorch, TensorFlow — detection & segmentation, stereo depth, camera calibration
Hardware
NVIDIA Jetson, Raspberry Pi, Luxonis OAK-D — RS485 / I²C / UART
Tools
ROS, Gazebo, Google Cloud, Git