Robotics Software - Perception ML

Location: South San Francisco / SF Bay Area, in-person

Company

hirify.global builds robotic systems that combine AI and simple equipment attachments to autonomously perform labor-intensive construction tasks, verification, and planning, initially for large-scale solar infrastructure.

What you will do

• Develop and deploy perception models for robot manipulation and navigation in dynamic outdoor environments.
• Shape the technical approach with a focus on real-world deployments.
• Research 3D scene understanding, detection, segmentation, pose estimation, tracking, reconstruction, world models, and VLMs.
• Work with multimodal sensor data including cameras, LiDAR, and tactile inputs.
• Build real and synthetic data pipelines, scalable training infrastructure, and validation systems.
• Develop performance metrics for large vision models and collaborate across teams.

Requirements

• M.S. or Ph.D. in robotics, computer vision, computer science, mechanical engineering, electrical engineering, or a related engineering discipline, or equivalent experience.
• 4+ years of hands-on experience developing perception solutions for robotics applications such as manipulation and navigation.
• Experience with detection, segmentation, pose estimation, tracking, 3D reconstruction, world models, or VLMs.
• Experience with synthetic data pipelines and robotics simulation infrastructure such as Isaac Sim, Gazebo, Blender, or Unity.
• Extensive experience with Python and ML frameworks such as PyTorch.
• Legally authorized to work in the United States. Comfortable taking ownership with light supervision and solving complex problems.

Culture & Benefits

• Join as an early team member with direct influence on the AI capabilities and product evolution.
• Work in a fast-paced startup environment with broad responsibilities.
• Address challenging robotics problems in harsh outdoor environments and critical infrastructure projects.
• Collaborate with experts in robotics and AI from Carnegie Mellon, Stanford, and MIT.