Principal Edge AI Firmware Engineer - Austin, Texas, United States
Originally posted 1 June 2026 by the employer.
About the role
Ambiq is seeking an Edge AI Firmware Engineer to build and optimize the embedded software stack that powers real-time, battery-powered on-device AI. You will develop Ambiq's AI runtimes, performance-critical operator libraries, and profiling/debug tooling for efficient inference on resource-constrained devices.
What you'll do
- Develop and support embedded AI runtimes (HeliaRT—an extension of TensorFlow Lite for Microcontrollers—and HeliaAOT) with a focus on portability, correctness, and performance. - Implement and optimize ML operator kernels and embedded libraries for on-chip acceleration across DSP, vector, and NPU architectures, including HeliaDSP and HeliaCore components. - Build and maintain on-device profiling and performance analysis tools that convert PMU counters into actionable insights. - Drive improvements in latency, memory footprint, and energy (joules/inference) through compute, bandwidth, and memory-hierarchy analysis. - Develop benchmark harnesses, microbenchmarks, and regression tests to verify numerical correctness and prevent performance regressions. - Enable customer integration across embedded environments and toolchains, including bare metal, FreeRTOS, and Zephyr.
What you'll need
- BS in Electrical/Computer Engineering, Computer Science, or a related field with 12+ years of relevant experience, or equivalent practical experience. - Strong experience designing, developing, and testing embedded software in C/C++. - Experience with embedded development workflows including Arm toolchains, GDB, J-Link/SEGGER-class probes, and CMake/Make build systems. - Solid understanding of compute, memory, and bandwidth/cache effects on deterministic latency and energy efficiency in constrained systems. - Strong debugging discipline with an emphasis on correctness, reproducibility, and performance regression prevention. - Proficiency with Git version control and ability to interpret hardware documentation such as datasheets and reference manuals.
Nice to have
- Python for profiling/analysis tooling, automation, and developer utilities, or Rust experience. - Familiarity with TensorFlow Lite for Microcontrollers or similar embedded inference runtimes. - Experience optimizing for embedded acceleration targets such as DSP, vector extensions, or NPU. - Familiarity with CMSIS-NN, CMSIS-DSP, or Vela. - Working knowledge of quantized inference (e.g., int8, per-channel) and embedded debugging implications. - Packaging/integration experience (such as CMSIS-Pack or CPM.cmake) or lab measurement experience using bench tools for power and debug analysis.
This role has been open 88 days — well above the 55-day median for Embedded Firmware Engineering roles.
Embedded Firmware Engineering · Systems Software
|
Open roles in category
730
|
Median days open
55 d
|
Median salary
$169k
|
See the full market breakdown ▾Category comparison, and who else is hiring
| Metric | Ambiq Micro | All employers we track in this specialty (730 roles · 83 employers) |
|---|---|---|
| Open roles in this specialty | 6 | 730 |
| Open roles in the wider Software, Firmware & Systems family | 12 | 6166 · 145 employers |
| Median days open | 88 d | 55 d (+33 d vs this employer) |
| Median salary (USD postings) | — | $169k |
Who's hiring in this category
- Qualcomm · 119 open roles · median 53 d
- AMD · 65 open roles · median 37 d
- Micron Technology · 61 open roles · median 87 d
- NVIDIA · 56 open roles · median 61 d
- Lattice Semiconductor · 46 open roles · median 40 d
- NXP Semiconductors · 32 open roles · median 34 d
How we counted: 730 open Embedded Firmware Engineering (Systems Software) roles from 83 employers tracked in the SemiconductorJobs index, counted 19 Oct 2026. Specialty figures count only roles carrying this exact specialty label, so an employer's related work in neighbouring specialties is not included there — it is counted in the wider Software, Firmware & Systems family row. Figures refresh nightly.