AI Engineer: Vision Models & Fusion

You'll join our existing AI engineer to divide and conquer the vision AI work as the company scales — the perception layer that turns multi-spectral camera feeds into reliable detection, tracking, and decision support for operators in the field.

‍

Experience

• 3–7 years in computer vision, deep learning, or perception systems.
• Strong with PyTorch (or equivalent), classical CV (OpenCV), and edge model deployment (TensorRT, ONNX Runtime, or equivalent).
• Hands-on production experience with object detection and multi-target tracking.
• Image fusion, sensor calibration, or multi-sensor work is a plus. ‍
  
  

What You'll Do

• Build and ship production-grade vision models across our FX-Ground camera line: object detection, multi-target tracking, EO + thermal image fusion.
• Own a slice of the perception roadmap end-to-end — training and evaluation through edge deployment on Jetson Orin hardware.
• Drive OpenCV-based tooling: ISP support, day–night fusion, sensor calibration. Classical CV that complements modern deep learning.
• Pick up cross-modal and RF fusion work as our radar partnership matures.
• Use our internal simulation pipeline (FX-Sim) as a first-class part of the model-development loop — close the synthetic-to-real gap.
• Partner with our FPGA / image-acceleration work on hardware-accelerated pipelines, and with the operator-experience team on inference deployment paths.
• Get into the field — debug models against real captures and drive the data flywheel that makes every deployment better than the last. ‍
  
  

Backgrounds That Fit

• Mid-level perception engineer from defence, robotics, autonomous driving, or surveillance industry
• Research-engineer profile from a strong CV lab (IIT / IIIT / equivalent)
• ML engineer with strong classical CV foundations alongside modern deep learning ‍
  
  

Email us with aCV and a short note on what you'd want to build at FieldX.

Use the subject line: Application for AI Engineer: Vision Models & Fusion