Engineer Robot Perception And Learning

Svaya Robotics Pvt. Ltd.; Hyderabad; On-site; INR 1,200,000 - 1,600,000; Full time

Job summary

Svaya Robotics Pvt. Ltd. is seeking an Engineer - Perception & Learning to advance the visual intelligence stack for its humanoid robots.

You will translate camera inputs into scene understanding and actionable motion planning commands, enabling autonomous tasks in manufacturing and beyond. You will work with CV/ML, robotics, and VLAM technologies, developing perception pipelines for real‑time operation and training world models for autonomous behavior.

Qualifications

• Experience in CV and ML algorithms for image segmentation and object detection.
• Strong understanding of PCL, filtering, diffusion and attention models.
• Background in deep learning, LLMs, and demonstrable projects in these fields.
• Familiarity with C++, multi‑threaded programming and GPU deployment.
• Ability to work in a fast‑paced startup development environment.
• Learning mindset and collaborative cross‑functional teamwork.

Responsibilities

• Develop traditional computer vision algorithms for detection and segmentation.
• Research and work with event-based, ToF, stereo cameras and integration.
• Collaborate with controls and planning teams to deploy autonomous stacks.
• Develop SL/World models and VLAs for Svaya Robots.
• Coordinate with cross-disciplinary engineers to evolve a robust robot platform.

Skills

Computer vision

Machine learning

C++

Multithreaded programming

GPU deployment

LLMs

Deep learning

Point cloud library

Diffusion models

Attention models

VLAMs

Reinforcement Learning

World Models

Education

MS or MTech in Robotics/Computer Vision/ML

Job description

Job Description:

About The Role

As Engineer - Perception & Learning, you will be working at the intersection of advanced sensor hardware, machine vision and real-time robot state estimation. You will work alongside our motion planning and application teams to build spatial and geometric perception systems to enable our robots to perceive, navigate and interact with the physical world. Your work spans the full spectrum of building the visual intelligence pipeline for our collaborative and bimanual humanoid robots - to translate the raw camera inputs to scene understanding and context to actionable motion planning command to enable robots to perform mission critical tasks in manufacturing and beyond. You will also work on visual pipelines used to train and condition large VLM/VLA and World models. The ideal candidate will have strong background in machine vision and robotics and have the willingness to learn and explore with a solutions mindset.

Your Work

• Develop traditional machine vision-based algorithms related to object detection, image segmentation, visual servoing using robotic arms, etc.
• Research and work with different types of cameras - event based, ToF, stereo cameras and develop algorithms and robotic applications with each of them.
• Work closely with controls, motion planning, and deployment teams to develop and deploy robust autonomic stack in loco-manipulation and grasping
• Work on cutting edge technology with VLAs and World Models to develop the autonomous stack for Svaya Robots.
• Collaborate with engineers from other disciplines and communicate design and technology priorities and provide constructive guidance to evolve a robust and reliable robot platform

What We're Looking For

• Experience in development and engineering of fundamental computer vision and machine learning algorithms with applications in image segmentation and object detection.
• Strong understanding of the point cloud library, filtering algorithms, and modern vision approaches including diffusion and attention models.
• Background and experience in advanced deep learning algorithms, LLMs and demonstrable projects in these fields with results.
• Familiarity with C++, multi-threaded programming, and high-performance optimization, deployment of these algorithms on GPUs.
• Ability and desire to work in a fast-paced startup development environment.
• Learning mindset with willingness to take on new challenges and solve unfamiliar problems.
• Should have good communication skills and be able to work collaboratively across cross-functional teams.

Nice to Have's

• Experience in Reinforcement Learning, Vision Language Action Models.
• Experience in development of simulation environments and build World Models.
• Experience in working with Robotic arms/Humanoids and deployment of autonomous features.

Education

MS or MTech (or higher) with specialization in Robotics, Computer Vision and/or ML

Requirements: