Autonomy Engineer — Planning & Orchestration

Jaide Health; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Jaide Health in the United States operates on-site in San Francisco and San Diego, focusing on spatial AI and autonomous robotics. This role targets engineers who have shipped planning or behavior layers for real robots and possess strong C++ and Python skills.

The team values leaders with experience in multi-agent coordination and robust failure handling, ready to contribute to a stealth, VC-backed startup environment.

Qualifications

• Shipped a planning or behaviour layer on real robots that operated without close supervision.
• Architecture: behaviour trees, state machines, task allocation, or equivalent.
• Failure handling for loss of comms, localisation or power mid-task.
• Operator interface: supervising several vehicles without babysitting any of them.
• Programming: strong C++ and Python.
• Domain-specific: multi-agent coordination, contested or comms-denied operation, human-robot supervisory control.

Skills

Planning

Architecture

Failure Handling

Operator Interface

Programming

Domain-Specific

Job description

Our work

We are a well capitalized stealth VC-backed startup building a new type of spatial AI capable of universally solving autonomy. We innovate at the foundational layer of AI by training our own AI models.

Our team

Our team is composed of AI pioneers and leaders from Google X, Google Brain, and Space Agencies. Several of us are repeat founders, with deep commercialization insights across multiple enterprise segments. We enjoy long, deep ideations around entirely unexplored AI use cases in autonomy (cars, drones, robots).

Location

San Francisco and San Diego (onsite). Active Field Testing

Technical Skills

• Planning: You have shipped a planning or behaviour layer on real robots that operated without close supervision.
• Architecture: Behaviour trees, state machines, task allocation, or equivalent. Explicit and inspectable rather than emergent.
• Failure Handling: What happens on loss of comms, localisation or power mid-task, designed rather than discovered.
• Operator Interface: Supervising several vehicles without babysitting any of them.
• Programming: Strong C++ and Python.
• Domain-Specific: Multi-agent coordination, contested or comms-denied operation, human-robot supervisory control.