Embodied Robotics AI Researcher - Sensor Fusion

PENTAS VISION PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Pentas Vision PTE. LTD. invites applications for an AI Researcher focused on embodied robotics.

The role involves frontier research in large-scale embodied AI models, data generation, training optimization, and evaluation, with emphasis on integrating sensor data across vision, LiDAR, IMU, and tactile modalities. You will iterate between simulation environments (MuJoCo, Isaac Sim, Omniverse, PyBullet) and real robotic hardware, collaborating with hardware teams to translate sensor

Qualifications

• Master’s or Ph.D. in Computer Science, Robotics, Electrical/Mechanical Engineering, or related field
• Familiarity with deep learning architectures for embodied AI and RL/IL or multimodal perception
• Experience in integrating hardware sensors into robotic systems and debugging software/hardware pipelines

Responsibilities

• Conduct frontier research in large-scale embodied AI models, including data generation, training optimization, and evaluation
• Track and assess state-of-the-art research and maintain/improve algorithmic frameworks
• Design and implement proof-of-concept systems and validate them in simulation and real robotic hardware
• Develop and deploy algorithms that leverage multimodal sensor data to enhance robotic intelligence and autonomy
• Collaborate with cross-functional teams to integrate algorithms into robotic platforms for robust real-world performance
• Work with hardware and sensor teams to translate sensor characteristics into algorithmic advantages
• Contribute to system integration and algorithm innovation, validating new sensors through AI benchmarks

Skills

Python

C/C++

ROS

PyTorch

TensorFlow

Multimodal perception

Reinforcement learning

Robotics

Education

Master's or Ph.D. in CS/Robotics/EE/ME

Tools

MuJoCo

Isaac Sim

Omniverse

PyBullet

ROS

Job description

Pentas Vision PTE. LTD. invites applications for an AI Researcher focused on embodied robotics.

The role involves frontier research in large-scale embodied AI models, data generation, training optimization, and evaluation, with emphasis on integrating sensor data across vision, LiDAR, IMU, and tactile modalities. You will iterate between simulation environments (MuJoCo, Isaac Sim, Omniverse, PyBullet) and real robotic hardware, collaborating with hardware teams to translate sensor