Principal Edge AI Firmware Engineer

This is a fully remote position, open to applicants in Texas.

📋 Description

• Develop and maintain Ambiq’s embedded AI runtimes (HeliaRT—our customized version of TensorFlow Lite for Microcontrollers—and HeliaAOT) with an emphasis on portability, accuracy, performance, and user experience.

• Implement and enhance ML operator kernels and embedded libraries for on-chip acceleration (DSP, vector, NPU), including the HeliaDSP and HeliaCore components.

• Construct and sustain on-device profiling and performance analysis tools, including translating PMU counters into actionable insights.

• Propel enhancements in latency, memory usage, and energy consumption (e.g., joules/inference) through analysis of compute/bandwidth and memory hierarchy.

• Create benchmark harnesses, microbenchmarks, and regression tests to ensure numerical accuracy and avert performance regressions.

• Facilitate seamless customer integration across various embedded environments and toolchains (bare metal, FreeRTOS, Zephyr).

• Enhance memory planning/runtime efficiency and oversee upstream/fork health; publish and maintain customer-facing resources (documentation, guides, examples, benchmarks).

⛳️ Requirements

• Bachelor’s degree in Electrical/Computer Engineering, Computer Science, or a related field, along with 12+ years of relevant experience (or equivalent practical experience).

• Extensive experience in designing, developing, and testing embedded software using C/C++.

• Strong debugging skills with a focus on correctness, reproducibility, and preventing performance regressions.

• Comprehensive understanding of compute, memory, and bandwidth/cache impacts on deterministic latency and energy efficiency in constrained environments.

• Ability to interpret hardware/software documentation (datasheets, reference manuals; familiarity with schematics is a plus).

• Proficient in Git (or an equivalent version control system).

• Effective use of AI-assisted development tools to enhance productivity while upholding engineering standards.

• Experience with embedded development workflows: Arm toolchains, GDB + J-Link/SEGGER-class probes, and CMake/Make build systems.

• Must be legally authorized to work in the United States for any employer. We do not provide sponsorship or take over sponsorship of employment visas (now or in the future) for this position.

🏝️ Benefits

• Health insurance

• 401(k)

• Remote work options