Computer Vision Engineer

At Harvested Robotics, we build  AI-powered laser-weeding systems  for farms in India. We capture high-resolution  RGB + NIR imagery , train custom models, and deploy them on rugged edge compute to identify weeds with speed, precision, and safety.

We’re looking for a  Computer Vision Engineer  who lives at the intersection of algorithms, data, and real-time edge deployment — someone obsessed with accuracy, latency, and pushing models into production on actual machines in the field.

What you'll do

Design, train, and optimise CV / ML algorithms for  weed detection, crop segmentation, and health classification .

Build and refine  data pipelines : labeling, augmentation, dataset versioning, and quality control.

Improve  accuracy, robustness, and FPS  across varied farm conditions (lighting, soil, rains, dust).

Deploy and optimise models on  edge hardware  (Jetson, Qualcomm, x86, custom accelerators) with tight compute budgets.

Implement  classical CV + deep learning  (OpenCV, geometric transforms, segmentation / detection networks).

Build and maintain  real-time inference pipelines  using  GStreamer, DeepStream , CUDA plugins, and custom kernels.

Convert and optimise models using  TensorRT, ONNX Runtime , quantisation (INT8 / FP16), and graph optimisation.

Work with the perception team on  NIR / RGB fusion , extrinsic calibration, and sensor synchronisation.

Analyse field failures and iterate on models  fast .

Build internal tools for  evaluation, visualization, and automated benchmarking .

What you need

Strong grounding in  computer vision, machine learning, and image processing .

Experience with  PyTorch / TensorFlow , ONNX, TensorRT, or similar optimisation stacks.

Comfort with  C++ / Python , CUDA, and real-time edge deployments.

Hands-on experience with  GStreamer  and / or  NVIDIA DeepStream  pipelines.

Solid understanding of model evaluation, metric design, class imbalance, and dataset bias.

Ability to work with large, messy, real-world datasets.

Experience with embedded GPU optimisation, Jetson NX / Orin deployments, or Qualcomm accelerators.

Familiarity with robotics perception, ROS, or sensor integration.

Your models directly control  when, where, and how our robot fires a laser at weeds . Precision and reliability define product success, safety, and farmer trust. This is not a lab role — your work runs on machines in actual farms every day.