Member of Technical Staff, Microsoft Robotics (Robotics Simulation)

Full Time

|

Redmond, WA

|

Microsoft

Microsoft’s Discovery and Quantum (MDQ) division develops and delivers advanced artificial intelligence (AI), cloud-enabled capabilities, and strategic technologies to help solve the world’s major challenges. From accelerating scientific discovery with advanced AI tools, to pioneering breakthroughs in quantum computing, to advancing robotics and AI capabilities that drive real-world impact, joining MDQ means building the future, partnering with fast-moving innovators, and operating in a high-impact, mission-driven environment.

At Microsoft Robotics within MDQ, we build and deploy technologies that enable people, robots, and AI agents to collaborate and achieve more.

We are building Microsoft’s platform for physical intelligence—an integrated robotics software and AI platform that brings together humans, robots, and agents through robotics AI models, innovative teaming solutions and experiences, physically grounded agentic AI workflows, trustworthy test and evaluation, and real-world customer-focused validation.

Built on Microsoft’s core platforms and delivered through a global ecosystem of partners and customers, this platform accelerates AI for the physical world and helps robotics solutions move from experimentation to reliable, scaled deployment.

We are hiring a Member of Technical Staff, Microsoft Robotics (Robotics Simulation) at the Senior level to lead the development of physics-ready 3D asset generation pipelines and the integration of reality capture technologies into Microsoft’s robotics simulation infrastructure.

This role focuses on bridging the physical and simulated worlds by creating high-fidelity digital representations of real-world environments, objects, and robots. The engineer will build workflows that transform raw sensor data—including photogrammetry, LiDAR scans, and depth maps—into simulation-ready 3D assets with accurate geometry, material properties, and physics parameters, enabling:

  • Photorealistic synthetic data generation

  • Digital twin construction

  • Sim-to-real model validation

Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees, we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

#MicrosoftRobotics #MDQ

Responsibilities

  • Design and build automated pipelines for converting reality capture data (photogrammetry, LiDAR point clouds, depth camera scans, and 360-degree imagery) into physics-ready 3D simulation assets with accurate geometry, collision meshes, material properties, and articulation definitions.

  • Develop and maintain toolchains for physics-ready 3D asset generation, including:

    • Mesh optimization

    • UV unwrapping

    • PBR material assignment

    • Collision hull generation

    • Mass and inertia parameter estimation

    • Annotation of semantic and functional properties

  • Integrate reality capture hardware and software workflows (e.g., NeRF, Gaussian Splatting, structured light scanning, photogrammetry reconstruction) with the simulation platform’s asset ingestion pipeline.

  • Build 3D reconstruction workflows that enable rapid creation of simulation environments from real-world facility scans, supporting robotics deployment planning, testing, and validation.

  • Create and maintain asset toolchains supporting industry-standard formats including:

    • USD/OpenUSD

    • glTF

    • FBX

    • OBJ

  • Develop synthetic data generation pipelines that leverage high-fidelity 3D assets to produce training data for:

    • Perception models

    • Manipulation models

    • Navigation models

  • Implement domain randomization across:

    • Materials

    • Lighting

    • Object placement

    • Camera viewpoints

  • Collaborate with robotics engineers, machine learning researchers, and perception scientists to:

    • Define asset fidelity requirements

    • Validate simulation-to-reality accuracy

    • Improve asset quality based on downstream model performance

  • Implement quality assurance and validation workflows for 3D assets, including:

    • Mesh integrity validation

    • Physics parameter consistency checks

    • Rendering fidelity verification

    • Simulation stability testing

  • Review code and technical designs to ensure adherence to team standards for:

    • 3D pipeline performance

    • Asset management

    • Data integrity

  • Stay current with advances in:

    • 3D reconstruction

    • Neural rendering

    • Asset generation research

  • Evaluate emerging technologies such as:

    • Generative 3D models

    • Neural Radiance Fields (NeRFs)

    • 3D Gaussian Splatting

Qualifications

Required Qualifications

  • Bachelor's degree in Computer Science or a related technical field and 4+ years of technical engineering experience with coding in one or more of the following languages:

    • C

    • C++

    • C#

    • Java

    • JavaScript

    • Python

OR

  • Equivalent practical experience.

Applicants who require a religious accommodation or a reasonable accommodation due to a disability during the application process may request accommodations through Microsoft's accommodation process.