Who are We
Field AI 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.
Learn more at https://fieldai.com.
About the Job
What You’ll Get To Do
Perception-Aware Mission Autonomy: Couple runtime perception outputs (e.g. semantic 3D scene understanding) with world information, to create a unified semantic scene graph that enables perception-aware real-time mission planning and execution with spatial reasoning, feasibility validation, online task replanning, and natural language driven robotic autonomy.
VLM-Based Long-Horizon Reasoning: Design and implement a VLM-based mission controller that observes the robot's camera view and scene graph, reasons about mission progress, and selects actions from reusable primitives and tools, with step verification, failure detection and recovery, online replanning, and feedback handling for natural language driven long-horizon missions.
Multi-Robot Mission Autonomy: Support the development of a multi-robot mission autonomy framework for task allocation, execution monitoring, and coordination across heterogeneous robots, and expand the robotics testing framework through unit and integration tests to ensure system reliability, safety, and performance.
What You Have
PhD in Computer Science, Electrical Engineering, Robotics, or a related field.
Advanced proficiency in Python programming, C++, ROS/ROS 2, Linux, Git, Docker
5+ years experience with AI-driven autonomy software deployed on real robots (e.g. task and motion planning, VLM/LLM-based planners, state machines, behavior trees) and low-level robotic manipulation skills
Ability to effectively and efficiently communicate with all teams, and to lead technical efforts across them
Strong problem-solving skills and proven ability to navigate complex software systems
Strong work ethic, highly self-motivated, and able to work independently while managing multiple priorities
The Extras That Set You Apart
Experience with simulation environments (e.g., Gazebo, Isaac Sim)
Experience with heterogeneous multi-robot systems (UGV, UAV, mobile manipulator)
Experience with LLM/VLM-based long-horizon planning and failure recovery in robotic systems
Skills Required
- PhD in Computer Science, Electrical Engineering, Robotics, or a related field
- Advanced proficiency in Python programming
- Advanced proficiency in C++
- Advanced proficiency with ROS or ROS 2
- Advanced proficiency with Linux
- Advanced proficiency with Git
- Advanced proficiency with Docker
- 5+ years of experience with AI-driven autonomy software deployed on real robots
- Experience with task and motion planning, VLM or LLM-based planners, state machines, or behavior trees
- Low-level robotic manipulation skills
- Ability to communicate effectively and lead technical efforts across teams
- Strong problem-solving skills and ability to navigate complex software systems
- Experience with simulation environments such as Gazebo or Isaac Sim
- Experience with heterogeneous multi-robot systems, including UGVs, UAVs, or mobile manipulators
- Experience with LLM or VLM-based long-horizon planning and failure recovery in robotic systems
What We Do
FieldAI is pioneering the development of a field-proven, hardware agnostic brain technology that enables many different types of robots to operate autonomously in hazardous, offroad, and potentially harsh industrial settings – all without GPS, maps, or any pre-programmed routes.
