Sr. Robotics Software Engineer, System Integration

FieldAI•Boston, MA

16h

About The Position

FieldAI is transforming how robots interact with the real world. Our growing R&D team is based in Boston, where we develop risk-aware, reliable, field-ready AI systems that tackle the hardest problems in robotics and unlock the potential of embodied intelligence. We take a pragmatic approach that goes beyond off-the-shelf, purely data-driven methods or transformer-only architectures, combining cutting-edge research with real-world deployment. Our solutions are already deployed globally, and we continuously improve model performance through rapid iteration driven by real field use. FieldAI is seeking passionate engineers to play a vital role in the development of our humanoid robot software stack. You will work with a focused team in a fast-paced environment to integrate perception, planning, locomotion, and manipulation subsystems into a single cohesive system that runs reliably on real hardware in unstructured, real-world environments. A core part of this role will be working with integrating and graduating research-grade capabilities into robust, production-quality systems. The ideal candidate will have a strong understanding of robotic software systems and the practical skills to deliver high-quality, maintainable code on a small, focused team.

Requirements

Bachelor’s or Master’s in Computer Science, Robotics, Electrical Engineering, or a related field (or equivalent industry experience).
7+ years hands-on experience developing and integrating robotics software, including work on physical hardware.
Strong C++ and Python proficiency with modern best practices; able to work in large, multi-language codebases.
Strong understanding of ROS/ROS2 and experience designing, building, and deploying nodes in complex robotic systems.
Solid understanding of real-time systems, inter-process communication, and resource-constrained embedded compute environments.
Experience hardening research/prototype code into production-quality software with testing and fault handling.
Strong problem-solving skills, attention to detail, and ability to work independently while managing multiple priorities.
Strong work ethic, self-motivated, and excellent written/verbal communication skills.

Nice To Haves

Experience with humanoid robots, legged locomotion platforms, or complex dexterous manipulation systems.
Familiarity with motion planning, whole-body control, or contact-rich manipulation pipelines.
Experience working with computationally constrained platforms and designing efficient, real-time software with low overhead.
Background in CI/CD, automated testing, and release engineering for robotics software.
Contributions to open-source robotics frameworks or tools.
Experience deploying robots in unstructured, real-world environments (construction, logistics, manufacturing, mining, defense).

Responsibilities

Develop and maintain the core software framework that composes perception, planning, locomotion, and manipulation into a deployable system on humanoid platforms.
Define and enforce subsystem interfaces, communication patterns, and data contracts for reliable, independent module development.
Own system bring-up, sensor calibration, and validation workflows for new sensor/platform revisions and configurations.
Partner with research engineers to take algorithms from prototype to production-quality, tested, maintainable code.
Identify and close reliability gaps with fault handling, performance budgets, integration/regression tests, and hardware validation.
Build repeatable “graduation” pipelines so new capabilities land without breaking existing functionality.
Design and run end-to-end integration tests across hardware and simulation.
Build tooling for automated diagnostics, telemetry, and post-run analysis to speed up debugging.
Coordinate integration milestones across teams, flag risks early, and keep the system continuously shippable.
Profile and optimize latency, throughput, and memory on embedded platforms under real-time constraints.
Harden the stack against real-world failure modes (sensor dropouts, comms loss, thermal throttling, degraded modes).
Implement runtime monitoring and health checks so the robot can detect, log, and recover from faults autonomously.