Software Engineer, Perception & Computer Vision

About Us:

Phridom AI - Ability Robotics is an early-stage robotics and AIcompany building the core systems behind embodied intelligence. Ourtechnologies help robots understand the physical world, learn intelligentbehaviours, and operate reliably in real environments. We’re still in stealth,but we’re already working with a select group of partners to validate oursystems in high-impact robotics applications. If you're excited to buildfoundational technologies for the next generation of robotics and wantmeaningful ownership over hard technical problems, we'd love to hear from you.

Role Overview:

As a Perception Engineer, you'll develop the vision systems thatenable robots to understand, track, and interact with the physical world inreal time. You'll work on object tracking, 3D reconstruction, state estimation,and interaction-aware perception, building algorithms that remain robust underocclusion, contact, and dynamic scene changes. Your work will directly improvehow embodied robots perceive and respond to their environments, enabling morecapable and reliable real-world deployments.

What you'll work on

1.                         Develop and deploy interaction-aware perception algorithms forrobotic systems, including object reconstruction, tracking, and stateestimation during interaction;

2.                         Design and implement high-performance 2D/3D tracking algorithms forstable perception in dynamic environments;

3.                         Develop 3D reconstruction and representation methods for interactionscenarios, including neural fields and explicit representations (e.g.,Gaussian-based, mesh-based), as well as 3D asset creation and scene generation;

4.                         Improve fine-grained object modeling and tracking in close-rangeinteraction scenarios, handling occlusion, contact, and rapid state changes;

5.                         Optimize model inference performance to meet real-time requirements(low latency, high throughput);

6.                         Deploy and integrate algorithms into robotic systems, resolvingreal-world performance and stability issues;

7.                         Collaborate cross-functionally to close the loop between data,models, and system performance;

8.                         Build evaluation pipelines to improve robustness and deployability.

Technical Requirements

Must Have

1.                         Bachelor's degree or above in Computer Science, Robotics, ElectricalEngineering, Automation, or a related field;

2.                          3+ years of experience incomputer vision or robotic perception, with experience in tracking, 3D vision,or interaction-related problems;

3.                          Strong fundamentals incomputer vision, including multi-view geometry, camera models, and 3Dreconstruction;

4.                          Experience with objecttracking methods (e.g., tracking-by-detection, multi-object tracking, 3Dtracking);

5.                          Proficiency in deep learningframeworks (e.g., PyTorch), with strong model development and optimizationskills;

6.                          Strong engineering skills,with experience deploying models on GPU or embedded platforms;

7.                          Strong debugging andproblem-solving skills in real-world systems.

Nice to Have

1.                         Experience in 3D reconstruction (e.g., SfM, SLAM, neural fields,Gaussian-based methods);

2.                          Experience with 3D objectdetection and tracking (e.g., multi-object or cross-view tracking);

3.                          Experience deployingalgorithms on real robotic systems (not limited to offline research);

4.                          Experience in modelacceleration and optimization (e.g., TensorRT, ONNX, quantization, pruning);

5.                          Experience with multi-sensorfusion (e.g., camera + depth or LiDAR);

6.                          Experience with large-scaledata processing or data pipelines;

7.                          Proficiency in English readingand writing, with the ability to understand technical literature.

Your Impact

1.                         Your perception systems will power real-world robotic deployments,helping robots understand objects, scenes, and interactions beyond controlledlaboratory settings.

2.                         You'll improve the reliability and robustness of robotic perceptionunder challenging conditions such as occlusion, motion, contact, andenvironmental uncertainty.

3.                         You'll help bridge cutting-edge 3D vision research and productionrobotics by deploying high-performance perception systems onto real roboticplatforms.

4.                         You'll play a key role in enabling next-generation embodied robots toperceive, track, and interact with the world more intelligently and reliably.

Why Join Us

Join us at an early stage and help build the core softwareinfrastructure behind humanoid and embodied robotic systems heading towardreal-world deployment. We move fast, ship often, and give engineers meaningfulownership—so you'll learn quickly, tackle high-impact challenges, and see yourwork running on real robots outside the lab. With active business across Chinaand beyond, you'll gain unique exposure to global robotics ecosystems,customers, and partners as the company scales.

Location

This role is based on-site in Singapore, working closely with theengineering team and robotic systems.

Occasional international travel to China and other regions may berequired for training, customer engagements, deployments, and partnercollaborations.

How to Apply

Send your resume and a brief introduction outlining your relevantexperience and interest in the role to info@phridom.com.

We'd also love to see examples of simulation environments, roboticsprojects, synthetic data pipelines, or other work you're proud of.