Computer Vision Data Scientist (Pune)

Codvo Private Limited; Pune District; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

A leading technology firm based in Pune is seeking a Computer Vision Data Scientist to design and optimize computer vision models for tasks such as object detection and human pose estimation. The ideal candidate will have strong expertise in various computer vision architectures and experience in deploying models using frameworks like TensorRT and OpenVINO. This role offers an opportunity to work on innovative projects within a collaborative and growth-oriented environment.

Qualifications

• Strong expertise in object detection architectures.
• Proven experience deploying optimized models using various frameworks.
• Familiarity with GPU acceleration and edge hardware constraints.

Responsibilities

• Design, develop, and optimize computer vision models for various tasks.
• Build and train deep learning models using specific frameworks.
• Write clean, scalable, and production-ready code in Python.
• Collaborate with cross-functional teams.
• Conduct performance evaluation and debugging of systems.

Skills

Object detection architectures (YOLO, Faster R-CNN, SSD)

Segmentation models (U-Net, Mask R-CNN)

Tracking algorithms (DeepSORT, ByteTrack)

Pose estimation frameworks (OpenPose, HRNet)

Model optimization techniques (INT8 quantization, FP16, pruning)

Strong Python programming skills

Tools

PyTorch

TensorFlow

TensorRT

OpenVINO

NVIDIA TAO Toolkit

Job description

Job Title: Computer Vision Data Scientist

About Us

At Codvo, we are committed to building scalable, future-ready data platforms that power business impact. We believe in a culture of innovation, collaboration, and growth, where engineers can experiment, learn, and thrive. Join us to be part of a team that solves complex data challenges with creativity and cutting-edge technology.

Key Responsibilities

• Design, develop, and optimize computer vision models for:
• Object Detection
• Image & Instance Segmentation
• Multi-Object Tracking
• Human Pose Estimation
• Build and train deep learning models using frameworks such as PyTorch or TensorFlow.
• Convert and optimize models for edge deployment using:
• TensorRT
• OpenVINO
• NVIDIA TAO Toolkit
• Perform model quantization, pruning, benchmarking, and latency optimization.
• Deploy models on edge hardware platforms (NVIDIA Jetson, Intel-based edge devices, etc.).
• Write clean, scalable, and production-ready code in Python.
• Collaborate with cross-functional teams including ML engineers, software developers, and hardware teams.
• Conduct performance evaluation, debugging, and continuous improvement of deployed systems.
• Stay updated with the latest research and advancements in computer vision and edge AI.

Required Qualifications

• Strong expertise in:
• Object detection architectures (e.g., YOLO, Faster R-CNN, SSD)
• Segmentation models (e.g., U-Net, Mask R-CNN)
• Tracking algorithms (e.g., DeepSORT, ByteTrack)
• Pose estimation frameworks (e.g., OpenPose, HRNet)
• Proven experience deploying optimized models using:
• TensorRT
• OpenVINO
• NVIDIA TAO Toolkit
• Strong Python programming skills.
• Experience with model optimization techniques (INT8 quantization, FP16, pruning).
• Familiarity with ONNX and model conversion pipelines.
• Understanding of GPU acceleration and edge hardware constraints.