Role:

Staying at the forefront of machine learning based autonomy stack and enable development of such. Enable data

· Develop in house simulation data engine, starting with object and lane based closed loop re-simulation using in-house tools and cloud infrastructure

· Research, develop, and implement state-of-the-art synthetic sensor simulation methods. Update the simulation data engine with controls to sensor modeling. Integrate with software stack

· Collaborate with suppliers or develop in house tools for next generation data based simulation stack. Explore open source simulation setup such as SUMO, WayMax etc.

· Collaborate with stakeholders across autonomy, mainly working on the AI/ML based software stack

Required Qualifications:

· Applied research that fuses cutting‑edge ML (e.g., NeRF, Gaussian Splatting, diffusion models) with classical simulation pipelines to boost realism and signal‑to‑noise.

· Deep knowledge of modern ML/DL — generative modeling, non‑linear optimization, sensor or graphics neural nets, and the math to adapt them to new simulation problems

· Master’s or Ph.D. in Computer Science, Robotics, Machine Learning, or a related field

· Expert-level proficiency in Python and ML libraries such as PyTorch or TensorFlow

· Expert-level proficiency in modern ML/DL — generative modeling, non‑linear optimization, sensor or graphics neural nets, and the math to adapt them to new simulation problems

· Proficiency in C++ and strong hands-on experience with software engineering design principles

Preferred Qualifications:

· Proven track record scaling ML workloads — multi‑GPU training, low‑latency inference, deterministic replay, and cloud orchestration for large‑scale simulation runs

· Deep understanding of 3D geometry and state estimation fundamentals.

· Experience in simulating/modeling real sensors (camera, lidar, radar, IMU, etc...), including noise modeling.

· Demonstrated research publications in top conferences (e.g. NeurIPS, ICLR, ICML, CVPR, RSS, CoRL, ICRA).