ML Engineer, Foundation Models (Autonomous Driving)

Location: Remote within the United States; San Francisco listed

Company

hirify.global is developing an autonomous, zero-emissions hauler using vision-based AI to reduce freight costs across the global logistics network.

What you will do

• Design and iterate on the vision-language-action foundation model architecture, including the VLM backbone, action decoder, and multimodal fusion pipeline.
• Build and optimize large-scale training infrastructure with distributed training, data pipelines, mixed precision, and efficient fine-tuning.
• Develop simulation-based evaluation and closed-loop training workflows using photorealistic neural rendering.
• Curate multimodal datasets covering real-world driving and synthetic scenarios.
• Translate research in diffusion and flow-matching action heads, reasoning-augmented VLAs, and world models into production-grade systems.
• Integrate model outputs into a real-time autonomous driving stack in collaboration with vehicle systems and controls engineers.

Requirements

• MS or PhD in Computer Science, Machine Learning, Robotics, or a related field, or equivalent industry experience.
• Strong proficiency in PyTorch, distributed training, and GPU-accelerated workflows.
• Strong knowledge of transformer architectures, attention mechanisms, and modern generative modeling, including diffusion and flow matching.
• Eligibility to work in the United States is required.

Nice to have

• Experience building or contributing to end-to-end autonomous driving systems.
• Publications at leading ML or robotics venues or significant open-source contributions.
• Experience with sim-to-real transfer, photorealistic simulation, neural rendering, reinforcement learning, imitation learning, or learning from demonstration.
• Experience as an early team member with high ownership and fast iteration.

Culture & Benefits

• Full-time remote work arrangement.
• Base salary, benefits, and equity compensation.
• Close collaboration within a small team of autonomous-vehicle industry veterans and engineers.
• Opportunity to build a production VLA system for autonomous freight from the ground up.

Hiring process

• AI tools may be used to compare applicant qualifications with the job description during interviews.
• A human reviews AI-generated output and makes the final hiring decision; eligible applicants may opt out of this AI-assisted comparison.