About the Role :

Join a team where cutting-edge visual intelligence meets real-world impact. In this role, youll lead the design and delivery of computer vision solutions that turn images and video into actionable insightspowering smarter products and better customer experiences. Youll work closely with engineers, data scientists, and product partners to shape technical direction, mentor team members, and drive high-quality execution from prototype to production.

With a hybrid work setup, youll enjoy the flexibility to collaborate in-person when it matters most while maintaining focus time for deep technical work.

Responsibilities :

- Lead end-to-end development of computer vision features using OpenCV and YOLO, from data understanding to deployment-ready solutions.

- Architect and implement object detection pipelines, including preprocessing, inference, and post-processing for accuracy and latency targets.

- Build, train, and fine-tune CNN-based models using PyTorch; run experiments and document results for reproducibility.

- Define technical standards for model development, code quality, versioning, and review practices across the team.

- Drive performance optimization (speed, memory, throughput) for vision workloads across varied environments.

- Collaborate with product and engineering stakeholders to translate requirements into scalable technical designs and delivery plans.

- Mentor engineers, guide troubleshooting, and unblock complex issues across data, training, and inference stages.

- Ensure reliable handoff to production by partnering on integration, monitoring expectations, and iterative improvements.

Minimum Qualifications :

- BTECH, BCA, BSC, MTech, MCA, MSc.

Preferred Skills :

- Experience improving model robustness across real-world conditions (lighting, occlusion, motion blur, scale variance).

- Strong experimentation discipline : dataset iteration, ablation studies, and metric-driven model selection.

- Experience with model optimization techniques such as pruning, quantization, or mixed-precision training/inference.

- Familiarity with deploying vision models into production workflows and collaborating closely with platform/engineering teams.

- Demonstrated leadership in mentoring, sprint planning, and driving cross-functional delivery for vision initiatives.