Senior Machine Learning Engineer

On behalf of my client, I am hiring for a Senior Machine Learning Engineer – End-to-End (E2E) to help develop and scale learning-based systems that connect multi-modal perception inputs to autonomous driving behavior. In this role, you will contribute to building safe, efficient, and human-like autonomy solutions for real-world freight operations.

You will work at the intersection of perception, prediction, and planning, contributing to unified learning pipelines that operate in closed-loop environments. This is a highly hands-on engineering role focused on execution, experimentation, and delivery.

• Develop and deploy end-to-end machine learning models that map multi-modal sensor inputs—including camera, LiDAR, radar, and maps—to driving-related outputs such as trajectories, cost functions, or intermediate representations
• Train and evaluate models using large-scale datasets from fleet logs, simulation environments, and synthetic data
• Analyze model performance, identify failure modes, and drive data-informed improvements in robustness and generalization
• Design and optimize training pipelines, data workflows, and evaluation strategies to improve iteration speed and model quality
• Contribute to architecture decisions involving transformers, imitation learning, reinforcement learning, BEV models, diffusion models, and vision-language-action systems
• Collaborate cross-functionally with Perception, Prediction, Planning, and Simulation teams to align learning systems across the autonomy stack
• Support integration of machine learning models into simulation and on-vehicle systems for closed-loop validation
• Improve experimentation workflows, tooling, and reproducibility practices
• Mentor junior engineers and contribute to technical discussions and engineering best practices

• Bachelor’s degree with 6+ years, Master’s degree with 4+ years, or PhD with 0–2 years of experience in Machine Learning, Robotics, Computer Science, or a related field
• Strong publication record in top-tier conferences such as NeurIPS, ICML, ICLR, CVPR, ICCV, or CoRL is preferred
• Experience developing and deploying machine learning models for autonomous systems, robotics, or complex decision-making environments
• Strong programming skills in Python and PyTorch, with the ability to write production-quality code
• Experience training and evaluating models on large-scale datasets using distributed compute environments
• Solid understanding of modern ML architectures used in end-to-end systems, including Transformers, BEV models, VLM/VLA systems, and diffusion models
• Proven ability to debug model behavior, analyze performance metrics, and improve model performance iteratively
• Experience influencing model architecture and training strategies
• Strong collaboration skills and experience integrating ML systems into broader autonomy pipelines

• Experience building end-to-end or mid-to-end models for autonomous driving or robotics
• Familiarity with vision-language models (VLMs) and vision-language-action (VLA) systems
• Experience with closed-loop simulation and evaluation frameworks
• Background in reinforcement learning or imitation learning for real-world systems
• Experience using distributed training frameworks such as Ray
• Understanding of vehicle dynamics, motion planning, or multi-agent systems

...