Computer Vision Engineer

Vintillix Global Innovations; Hyderabad; On-site; INR 800,000 - 1,200,000; Full time

Job summary

Vintillix Global Innovations in Hyderabad is seeking candidates for a role focused on advanced computer vision. The ideal candidate will design and optimize pipelines for edge devices, deploying deep learning models on platforms like Jetson and Raspberry Pi.

This position requires a strong understanding of camera geometry, CNN architectures, and proficiency in Python or C++. Candidates with experience in robotics or real-time video analytics are preferred.

Qualifications

• Deep understanding of computer vision fundamentals.
• Experience with robotics, AI, and embedded systems.
• Strong proficiency in Python or C++.

Responsibilities

• Design and optimize computer vision pipelines for edge devices.
• Deploy deep learning models on embedded platforms.
• Optimize AI inference pipelines.

Job description

We are currently looking for immediate joiners for multiple open positions. Candidates who are available to join at the earliest or serving short notice periods are encouraged to apply.

About the Role

The ideal candidate should have a deep understanding of computer vision fundamentals, real-time AI inference, edge optimization, and embedded system constraints. This role involves working on robotics and intelligent systems requiring low-latency perception, tracking, navigation, and human interaction capabilities.

Key Responsibilities

• Design, develop, and optimize computer vision pipelines for edge devices.
• Deploy deep learning models on embedded platforms such as Jetson, Raspberry Pi, RK3588, Intel NUC, and other industrial SBCs.
• Build real-time systems.
• Optimize AI inference pipelines.

Work with camera interfaces including

• Develop low-latency pipelines using OpenCV, GStreamer, and hardware accelerators.
• Work closely with robotics, AI/ML, and embedded teams for end-to-end product integration.
• Debug performance bottlenecks involving memory, thermal limits, FPS, and power optimization on edge hardware.

Required Skills

Core Computer Vision Knowledge

Strong understanding of:

• Camera geometry & calibration
• Feature extraction & matching
• CNN architectures for vision
• Transformer-based vision models

Technical Skills

• Strong proficiency in Python and/or C++
• OpenCV (advanced level)

Deep learning frameworks:

• PyTorch
• TensorFlow

Experience with

• TensorRT
• CUDA
• ONNX
• GStreamer
• OpenVINO
• Model optimization for edge inference

Embedded & Edge AI

• RK3588 or similar ARM SBCs
• Industrial embedded AI hardware
• Hardware acceleration and low-power AI deployment

Preferred Qualifications

• Experience in robotics or autonomous systems
• Experience with real-time video analytics
• Knowledge of sensor fusion (IMU + Vision)
• Experience with edge AI model compression techniques
• Understanding of hardware-software co-optimization
• Experience building production-grade AI systems