About the Role :

We're building intelligent machines that interact with the physical world. As our AI Engineer, you'll develop and deploy AI models that run at the edge - powering real-time decisions in dynamic environments.

Responsibilities :

- Develop and train deep learning models for object detection, segmentation, tracking, and defect classification

- Build depth-based inspection systems using stereo vision and structured light

- Optimize models for real-time inference on edge devices

- Build pipelines for data collection, labeling, augmentation, and retraining

- Collaborate with optics, embedded, and software engineers to deploy models in the field

- Evaluate and benchmark system performance in real industrial environments

Requirements :

Must-Have :

- 3-4 years experience building and deploying CV/AI systems

- Hands-on experience with NVIDIA DeepStream, GStreamer, Triton Inference Server, or TensorRT to architect ultra-low-latency, high-throughput vision pipelines from camera ingest to optimized model deployment on edge GPUs.

- Proficiency in Python, PyTorch/TensorFlow, and OpenCV

- Experience with image/video datasets, augmentation, and preprocessing

- Understanding of camera geometry, image noise, and lighting variation

Nice-to-Have :

- Experience with stereo vision, structured light, or depth reconstruction

- Exposure to model quantization, pruning, or edge deployment (e.g. TensorRT)

- Experience with MLOps or training data pipelines

- Solid understanding of 1D/2D metrology and classical computer-vision techniques (e.g., sub-pixel edge detection), enabling accurate dimensional inspection alongside deep-learning models.

- Experience writing/ customizing CUDA kernels to accelerate inference pipelines, minimizing latency and maximizing throughput on edge devices.

What We Offer :

- The opportunity to build a hardware startup in India from scratch

- Build CV models that power machines in the real world

- A mission-driven, engineering-first culture at the frontier of industrial AI