Senior Computer Vision Engineer

Neurabit Solution; Sambalpur; On-site; INR 1,800,000 - 2,800,000; Full time

Job summary

Neurabit is seeking a Senior Computer Vision Engineer to own end-to-end CV systems, from architecture and model selection to edge deployment and production hardening.

You will work with the founding team on flagship projects across multi-camera passenger counting, PPE/zone compliance detection, and related edge AI solutions, shipping to customers within weeks.

Qualifications

• 4+ years of production computer vision experience in live deployments.
• Experience with detection and tracking in real-world scenes.
• Experience deploying models on edge hardware (Jetson, similar).
• Strong Python and C++ for performance-critical paths.
• Experience debugging CV systems in field deployments.
• Comfort with Linux, Docker, and Git workflows.

Responsibilities

• Design and ship multi-camera CV pipelines for detection, tracking, and counting in constrained edge environments.
• Build and tune object tracking systems (ByteTrack, DeepSORT, or similar) for occlusion-heavy, real-world scenes.
• Optimize models for edge inference — quantization, pruning, TensorRT/ONNX conversion — targeting NVIDIA Jetson (Orin/Xavier/Nano).
• Own accuracy in the field: develop evaluation protocols and debug production failures.
• Work with RTSP/RTMP camera streams and handle unreliable networks, building robust pipelines.
• Write clean, maintainable Python/C++ and mentor mid-level engineers on CV best practices.

Skills

Python

C++

YOLO-based detection

Edge deployment

TensorRT

Tools

TensorRT

ONNX Runtime

OpenVINO

DeepStream

Jetson platform

Job description

# Senior Computer Vision EngineerHybridFull-time4+ yearsPosted 5 Jul 2026CompetitiveApply Now## About NeurabitNeurabit is a bootstrapped, DPIIT-recognised, deep-tech company building edge AI, computer vision, and physical AI systems that run where the internet doesn't. Our systems are deployed across 7+ countries — from passenger analytics on public transit fleets to industrial safety monitoring, substation surveillance, and sports analytics. We're a team of ~18 engineers who ship real hardware-software systems into messy, real-world environments: moving buses, dusty factory floors, remote substations.We're not a research lab. Models here don't live in notebooks — they live on Jetsons bolted inside vehicles and on factory walls, running 24/7.## The RoleYou'll own computer vision systems end to end: from architecture and model selection through optimization, edge deployment, and production hardening. You'll work directly with the founding team on flagship projects — multi-camera passenger counting, PPE and zone compliance detection, ANPR, crowd intelligence, and driver monitoring — and your decisions will ship to paying customers within weeks, not quarters.## What You'll Do* Design and ship multi-camera CV pipelines for detection, tracking, and counting in constrained edge environments* Build and tune object tracking systems (ByteTrack, DeepSORT, or similar) for occlusion-heavy, real-world scenes* Optimize models for edge inference — quantization, pruning, TensorRT/ONNX conversion — targeting NVIDIA Jetson (Orin/Xavier/Nano), Hailo, and similar accelerators* Own accuracy in the field: design evaluation protocols, debug failure modes from real deployment footage, and close the gap between lab metrics and production performance* Work with RTSP/RTMP camera streams, handle unreliable networks, and build pipelines that degrade gracefully* Write clean, maintainable Python/C++ and mentor mid-level engineers on CV best practices* Collaborate with hardware, backend, and product teams to scope what's technically feasible before we commit it to a client## Must-Haves* 4+ years of production computer vision experience — models you built are (or were) running in live deployments, not just demos or papers* Deep hands-on experience with detection and tracking: YOLO family, transformer-based detectors, multi-object tracking* Proven edge deployment experience: TensorRT, ONNX Runtime, OpenVINO, or DeepStream on Jetson-class hardware* Strong Python; working C++ for performance-critical paths* Solid grasp of the full pipeline: data collection, annotation strategy, training, evaluation, deployment, and monitoring* Experience debugging CV systems from field footage — you know that production accuracy problems are rarely solved by "train a bigger model"* Comfort with Linux, Docker, and Git-based workflows## Nice-to-Haves* Video analytics at scale: GStreamer, FFmpeg, MediaMTX, or VMS integration* Re-identification, pose estimation, or face recognition in production* Experience with counting/occupancy systems, ANPR, or industrial safety CV* Familiarity with camera hardware: ONVIF, RTSP tuning, lens/FOV selection, IR/low-light constraints* Exposure to MLOps for edge fleets: OTA model updates, remote monitoring, telemetry* Contributions to open-source CV projects## Why Neurabit* Real ownership — you'll be the senior-most CV voice in the company, shaping architecture decisions across every project* Ship fast, see impact — your work goes live on buses, in factories, and at government sites within weeks* Hard problems — edge constraints, moving cameras, occlusion, low light — the kind of CV that doesn't have a Kaggle solution* Competitive salary, meaningful growth path toward CV Lead / Architect as the team scales* Equity in our growth story and growing with us.## How to ApplyApply via the form linked — include your resume and be ready to talk through a real production CV problem you've solved.*Neurabit is an equal opportunity employer.*