Hardware Podcasts

Embedded Systems Engineer Discusses AI-Driven Testing Revolution

OnTrack · 3 Jun 2025 · 56m · Episode 300

AI in practice: 2 real uses of AI described

What this episode covers

Ari Mahpour, an Embedded Systems Engineer at Rivian with prior experience at NASA JPL and Virgin Hyperloop, discusses the integration of AI and DevOps into embedded hardware development. He demonstrates 'vibe coding' with an Arduino using voice commands and LLMs, explaining how AI agents can autonomously write, compile, and test firmware. Mahpour also covers the challenges of managing hardware revisions, the importance of Model Context Protocol (MCP) for tool guardrails, and the future of AI in automated PCB design and testing.

AI in practice

Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.

Engineering & simulationLLM (Generic)30 seconds vs 1 hour

An LLM analyzed mechanical fixtures and IC data sheets to generate a complete list of test vectors (Python dictionary lists) for an end-to-end test, reducing analysis time from one hour to 30 seconds.

“I gave it my test environment just for the setup routine, and I said, write me all the test vectors in like one huge list or Python dictionary lists … it gave me based on the data sheets … It did it in like 30 seconds.”

Ari Mahpour · Hear it at 43:12

DesignLLM (Generic)50% time saved

An LLM is used to review schematics and write boilerplate embedded software by identifying ICs and their interfaces, saving approximately 50% of the time required for initial software development.

“Imagine an LLM looking at a schematic, and then writing all the boiler plate software for your embedded device, because it knows all the ICs. … Did it save you like at least 50% of your time for a boiler plate? Absolutely it did.”

Ari Mahpour · Hear it at 50:59

Most relevant to

large enterprises

Topics

Mentioned

Companies
Rivian, NASA JPL, Virgin Hyperloop, Octopart
Products
Arduino, Nvidia Jetson Orin
Also
Claude, GitHub

Related episodes from other shows

Other shows on the same ground, closest first.

  • Coredump Sessions · 1h 01m

    #021: Hardware at Software Speed: How BootLoop Is Bringing AI to the Bench for Firmware Teams

    Noah Pasek-Nelson and Chris Markus, co-founders of BootLoop, explain how their AI platform accelerates the firmware lifecycle by combining deep hardware context with automated hardware-in-the-loop testing. They discuss how ingesting schematics and data sheets eliminates hallucinations, allowing the system to generate, flash, and validate code on physical devices like oscilloscopes and logic analyzers. The founders also cover BootLoop's security posture, pricing model, and its 'Sentinel' product for automated field debugging.

    AI & machine learningEmbedded firmware
    7 chapters

  • Coredump Sessions · 55m

    #007: AI, Open Source, and the Future of Embedded Development: How Much Code Will We Actually Write?

    François Baldassari, CEO of Memfault, and Thomas Sarlandie, Field CTO of Memfault, host a panel with Jonathan Beri, CEO of Golioth, and Dan Mangum, CTO of Golioth, to discuss the intersection of AI, open source, and embedded development. The group analyzes the maturity of edge AI for audio and video processing, the challenges of integrating LLMs into hardware due to rapid model iteration, and the current state of using AI for firmware development. They conclude that while AI is transforming code generation and review, open source remains critical for training models and providing trusted, complex infrastructure like Zephyr and FreeRTOS.

    Embedded firmwareAI & machine learning
    9 chapters

  • The Pragmatic Embedded Podcast · 55m

    Crossover with Embedded AI Podcast

    Jeff Gable, Luca, and Ryan Torvik discuss integrating Large Language Models (LLMs) into embedded systems engineering workflows, emphasizing that AI must augment rather than replace rigorous engineering discipline. They identify 'vibe coding' as a critical anti-pattern where developers lose control of architectural decisions by letting AI generate too much code at once, leading to unmanageable outputs and hallucinations. The hosts advocate for strict context management, test-driven development (TDD), and small, incremental commits to maintain deterministic quality, particularly in safety-critical domains like medical devices and automotive systems. They conclude that while LLMs accelerate prototyping and boilerplate generation, human code review and ownership remain non-negotiable for reliable production software.

    Embedded firmwareDebugging & failure analysis
    8 chapters

  • The Pragmatic Embedded Podcast · 40m

    Does DevOps Make Sense for Embedded Systems?

    Jeff Gable and Luca Engeni discuss why DevOps and Agile principles are essential for embedded systems, particularly in safety-critical industries like medical devices and aerospace. They argue that while hardware iteration is slower than software, fixed cadences for PCB releases can still accelerate feedback loops. The conversation highlights the shift toward over-the-air updates, using Tesla as a case study for the new safety challenges introduced by connected vehicles.

    Embedded firmwareValidation & product-market fit
    6 chapters

  • Embedded.fm · 1h 07m

    500: Nerding Out About the Ducks

    Komathi Sundaram, a principal test engineer at Cruise, discusses her career transition from software development to embedded testing and her philosophy on automation. She details the architecture of hardware-in-the-loop (HIL) test benches, explaining how to orchestrate real-world scenarios like NFC taps and audio loops for devices under test. Sundaram emphasizes the importance of continuous integration, using Docker for environment consistency, and designing 'brick test beds' to safely allow developers to break systems during innovation.

    Embedded firmwareConnected products & IoT
    8 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by OnTrack. The episode itself belongs to its publisher.