Senior Computer Vision Engineer
Pivotchain Solutions (company site, opens in a new tab)4+ yrsPuneOn-siteDirect career pageEst. 12–22 LPA
Posted on 3 Sept
Reach people at Pivotchain Solutions
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Pivotchain Solutions you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Own the end-to-end lifecycle of detection, tracking, and re-identification models processing live video from thousands of cameras in real deployment environments.
- Design, train, and optimize models to run efficiently on edge and on-premise GPUs with techniques like TensorRT, ONNX, and quantization.
- Develop evaluation pipelines to measure real-world accuracy and collaborate with deployment engineers to fine-tune models for customer-specific camera setups and scenes.
Minimum Requirements
- 4+ years of professional experience in computer vision or deep learning with proven production model deployment.
- Strong programming skills in Python and PyTorch with deep knowledge of modern detection and tracking architectures.
- Experience in optimizing inference for real-time applications in resource-constrained environments.
- Work Experience Required: 4+ years in computer vision / deep learning with production models shipped.
Ideal Candidate Profile
- Technical expert comfortable bridging research models to running production on real-world edge devices under operational constraints.
- Experienced in hands-on model optimization and tuning for live video analytics in critical, high-stakes environments.
- Operates with a pragmatic approach prioritizing real-world field performance over just benchmark metrics.