Helix AI Engineer, Figure

• If you've spent time below the Java/Kotlin layer — writing C/C++ via the NDK, implementing custom HALs, or building zero-copy sensor pipelines — this role was built for you
• Deep expertise in Android NDK (C/C++) — custom HAL development, USB Host/AOA protocol communication, and direct hardware interfacing below the standard SDK layer
• Proven experience architecting real-time, low-latency data pipelines for high-bandwidth sensors — zero-copy memory, real-time concurrency, and synchronization with zero frame drops
• Mastery of Android system resource management: CPU/GPU workload optimization, thermal and battery constraints, foreground services, and WorkManager
• Strong proficiency in both C/C++ (NDK) and Kotlin/Java for Android
• Experience shipping production Android applications in hardware-connected, latency-critical environments
• Proven track record shipping and maintaining production Android applications at scale — including crash rate management, OTA update rollout strategies, real-time telemetry and monitoring pipelines, and sustaining reliability across a large, diverse active user base spanning multiple device configurations and Android OS versions

Desirable

• We're looking for an Embedded Android Systems Engineer with deep expertise in low-level Android systems, the NDK, and real-time sensor and video pipelines
• . This is not a standard Android app role — you'll be building the mobile application that interfaces directly with our custom sensor hardware over USB, ingests high-frequency camera and IMU data in real time, and runs on-device AI inference at the edge
• Build and own the Android application that serves as the primary mobile interface to Figure's humanoid robots, connected via USB Host / Android Open Accessory protocols
• Architect high-throughput, zero-drop data ingestion pipelines for high-FPS image sensors and high-frequency IMU data, using zero-copy memory techniques and real-time concurrency models
• Implement custom hardware abstraction layers (HAL) and leverage the Android NDK (C/C++) for high-performance, low-latency processing
• Optimize CPU/GPU workloads for real-time edge filtering under strict thermal and battery constraints, using foreground services and WorkManager for bulletproof background operation
• Integrate on-device AI inference libraries (TFLite, MediaPipe, ONNX Runtime, OpenCV) for real-time computer vision and sensor fusion
• Implement low-latency video streaming protocols (e.g. WebRTC)