Embedded Software and Edge AI Engineer

Location: Los Angeles, CA or Louisville, KY

About the work

Bring AstraSense and AQFM software onto real computing platforms. Build the path from sensor acquisition to health inference and communications, with measurable timing, resource use and failure behavior. Work across embedded Linux and, where the target requires it, microcontroller, RTOS or bare-metal software.

What you will do

• Develop modular C/C++ and Python components for telemetry acquisition, buffering, real-time signal processing, health inference and communications.
• Implement and debug sensor drivers, interrupts, DMA and ADC interfaces on the selected hardware; assess architectures intended to handle more than 100 sensor channels.
• Profile end-to-end latency, memory and power-related constraints. Optimize model execution toward the specified 100 ms capture-to-detection budget and document overload and degraded-input behavior.
• Build and test CAN/CAN-FD, serial and Ethernet interfaces; support ARINC 429/664 integration where required by the chosen aircraft interface. Define message rates within the applicable 1 Hz to 1 kHz requirement range rather than assuming every output uses the same rate.
• Implement local high-rate logging, reproducible timestamps and secure data offload for ground analysis, with defined retention and access behavior.
• Implement deterministic supervisory checks, bounded interfaces, error handling and safe degraded modes as defined by system requirements; keep operator authority explicit.
• Maintain repeatable builds, deployment scripts, unit/integration tests and requirements traceability. Apply software-assurance practices appropriate to the project without representing prototype work as certified.

What you bring

• Practical embedded Linux development and strong C++ or Python skills, with ability to work across hardware/software interfaces.
• Experience debugging sensor or communications interfaces and measuring runtime behavior on target hardware.
• Ability to write tested, documented modules and work with version control and continuous integration.
• Working knowledge of embedded C/C++, real-time data paths or vehicle/industrial buses relevant to the assigned subsystem.

Useful additional experience

Microcontrollers and RTOS development, NVIDIA Jetson or ARM platforms, ROS 2, CAN, TinyML/CMSIS-NN/TFLite Micro, model quantization, ARINC interfaces, or participation in DO-178C- or ISO 26262-oriented projects.

First 90 days: scope to agree

Agree a scoped first-90-day objective: a tested development-kit data path from sensor input through feature extraction to a health update over CAN, including timing/resource measurements, interface documentation and failure-handling tests. Select the platform and performance acceptance criteria before implementation.

About AstraQua

AstraQua is developing a modular autonomy architecture with AQFM as its shared intelligence foundation. Specialized agents contribute perception, reasoning, health and coordination. AstraSense is the health-intelligence agent, with electrified aviation as an initial research application; it connects condition and remaining capability with mission decisions. Our approach to safe AI emphasizes defined operating boundaries, deterministic safety controls, operator authority and behavior designed for verification and validation.

How to apply

Email your resume, job title and preferred location (Los Angeles, CA or Louisville, KY) to careers@astraqua.com. Include a nonconfidential project example.