Field AIÂ is transforming how robots interact with the real world. We are building risk-aware, reliable, and field-ready AI systems that address the most complex challenges in robotics, unlocking the full potential of embodied intelligence. We go beyond typical data-driven approaches or pure transformer-based architectures, and are charting a new course, with already-globally-deployed solutions delivering real-world results and rapidly improving models through real-field applications.
About the Job
At Field AI, we’re building robots that don’t just sense the world, they reason about it and make intelligent decisions in real time. As a Robotics Autonomy Engineer - Reasoning , you’ll design and deploy scalable, interpretable world models and decision-making systems that let our robots operate safely and intelligently in dynamic, uncertain environments. You’ll fuse multi-modal sensing with semantics and risk analysis, enable real-time decision-making under uncertainty, and embed transparency, adaptability, and fail-safes into the autonomy stack. This is a role for an engineer who thrives at the frontier of AI and robotics—someone excited to push beyond perception into true reasoning, and to see their work come alive in robots that adapt and succeed in the real world.
What You’ll Get To Do
• 1. World Modeling & Representation
• Design and iterate on scalable, interpretable spatio-temporal-semantic world models.
• Fuse multi-modal sensing with semantics and embedded risk analysis.
• Ensure real-time performance with low latency in dynamic, uncertain environments.
• 2. Reasoning & Decision-Making
• Develop reasoning and decision-making systems that remain reliable under uncertainty and enable success in complex real-world missions.
• Validate reasoning systems across challenging edge-case scenarios (e.g., sudden obstacles, degraded sensing).
• Integrate reasoning with perception and control for closed-loop autonomy at high mission success rates.
• 3. Safety, Transparency & Adaptability
• Implement diagnostic layers that log reasoning steps for interpretability and post-mission analysis.
• Develop fail-safe behaviors that trigger under uncertain or conflicting world-state estimates.
• Ensure adaptability to new environments while always prioritizing safety.
The Extras That Set You Apart
• Background in semantic reasonings, human-robot interaction, or multi-agent system.
• Familiarity with ROS or similar middleware for robotics development and deployment.
• Knowledge of hardware-aware optimization and acceleration of autonomy stacks (e.g., real-time constraints, GPU/TPU programming).
• Experience deploying autonomy on physical robotic platforms in real-world field environments (e.g., outdoor, off-road, degraded sensing).