Perception & Intelligence Engineer

JD – Perception & Intelligence Engineer

Location: Pune

Experience: 2-5 Years

Education: B.E. / B.Tech / M.Tech in Computer Science, AI, Robotics, or related fields

Employment Type: Full-time

Reports To: Engineering Manager

About the Company:

We founded Sakar Robotics to collapse fragmented point solutions into a single extensible mobile manipulation platform. Traditional automation requires bespoke integration per workflow—slow to deploy, rigid to evolve. We built a composable stack where perception, autonomy, manipulation and orchestration cooperate natively.

Guided by field feedback across regulated, high‑mix and throughput‑critical domains, we iterate on production reality—not lab abstractions—building durable leverage for customers.

Our mission is to deliver a unified robotics platform that can be rapidly configured to execute diverse workflows—reducing time‑to‑value, elevating safety, and embedding continuous improvement loops into daily operations.

Role Summary

We are looking for a Perception / Computer Vision Engineer to design, develop, and deploy real-time vision systems for autonomous and intelligent robotic platforms. This role involves working closely with real sensor data, production constraints, and cross-functional robotics teams to convert perception algorithms into reliable, deployable systems.

Key Responsibilities:

1. Computer Vision & Perception Development

• Design and implement computer vision pipelines using OpenCV and Python
• Develop and fine-tune YOLO-based object detection models (YOLOv5 / YOLOv7 / YOLOv8)
• Work on object detection, tracking, classification, and region-of-interest extraction
• Handle challenges related to lighting variation, motion blur, occlusion, and noise
• Perform camera calibration, distortion correction, and image preprocessing

2. Model Training & Optimization

• Prepare and manage datasets: annotation, augmentation, and validation
• Train, evaluate, and fine-tune YOLO models for real-world performance
• Optimize models for latency, FPS, and memory usage
• Analyze false positives / false negatives and improve model robustness

3. Deployment & Integration

• Integrate perception modules with robotics software stacks
• Ensure real-time inference on edge/embedded systems
• Collaborate with autonomy, controls, and hardware teams
• Debug perception issues during field testing and deployments

4. Engineering & Collaboration

• Write clean, modular, and well-documented Python code
• Participate in design reviews and technical discussions
• Take ownership of perception components from concept to deployment
• Continuously improve system reliability and performance

  Must-Have Skills:

• Strong proficiency in Python
• Hands-on experience with OpenCV
• Practical experience with YOLO (training, inference, evaluation)
• Solid understanding of computer vision fundamentals
• Experience working with real-world camera data
• Experience with Deep Learning frameworks (PyTorch / TensorFlow)
• Knowledge of ROS / ROS2
• Experience in robotics or industrial automation
• Model deployment on edge devices (Jetson, CPU-only, etc.)
• Basic understanding of sensor fusion concepts

Soft Skills:

• Strong communication and coordination
• Ownership and accountability
• Problem-solving and proactive approach
• Adaptability in a fast-paced environment
• Team collaboration and positive attitude

What We Value:

• Ability to move from research → production
• Strong problem-solving and debugging skills
• Ownership mindset and accountability
• Comfort working in a fast-paced startup environment
• Curiosity and willingness to learn continuously

Why Join Us:

• Work on real robots in production environments
• Solve meaningful perception problems, not just lab demos
• High ownership and direct impact on deployed systems
• Collaborative team with deep technical focus

Ready to make an impact?

Share your resume or even a short note about why you’d love to join us at

We’re excited to meet passionate people who love taking ownership and growing fast!