Rivian’s Roadmap to AI Architecture and Autonomy with Founder and CEO RJ Scaringe
Summary
RJ Scaringe outlines Rivian's strategic reset from rules-based autonomy to an end-to-end neural-net architecture and a vertically integrated data stack. The company rebuilt its perception, compute, and data pipelines (Gen2) to enable large-scale model training, onboard inference, and a continuous training loop fed by its growing fleet. Rivian is designing its own inference chip to reduce the per-vehicle cost of real-time neural-net driving and is shifting vehicle electronics to a software-defined, zonal architecture to enable fast OTA feature development. The conversation also covers product strategy (including the upcoming R2) and a broader vision of cars as software platforms that deliver ongoing feature improvements and differentiated customer experiences.
Key Takeaways
- 1Rivian moved from rules-based autonomy to end-to-end neural-net architectures to handle real-world driving complexity.
- 2Vertical integration across sensors, in-vehicle compute, and data pipelines is critical to scale neural-net autonomy.
- 3Onboard inference is the dominant cost driver, motivating Rivian to design its own custom inference chip.
- 4Software-defined, zonal vehicle architectures enable rapid OTA feature deployment and cross-domain coordination.
- 5Fleet data and a growing car park create a sustainable data advantage versus independent autonomy companies.
Notable Quotes
"By 2030, it'll be inconceivable to buy a car and not expect it to drive itself."
"Not a single line of shared code, not a single piece of common hardware on the perception or on the compute side."
"The really expensive part of the system is actually the onboard inference... that's like an order of magnitude more expensive than any of the perception stack."
"The world doesn't need another Model Y, the world needs another choice."
Episode questions
Why did Rivian reset its autonomy platform after launch?
They started with a rules-based 1.0 approach and concluded it would not scale to neural-net-driven autonomy; a clean-sheet redesign (Gen2) with new hardware and data infrastructure was necessary to build the training loop and models they needed.
Why build an in-house inference chip instead of buying one?
Onboard inference is the dominant cost in deploying autonomy; designing their own chip was a cost-driven decision to make high-performance inference affordable enough to include in every vehicle.
What makes Rivian's data advantage unique compared with independent autonomy companies?
Rivian controls the perception platform, can collect raw sensor signals, has a growing car park where every vehicle contributes data (including triggered corner cases), and can feed that into large-GPU training — an end-to-end loop many independents lack.
How will software-defined architectures change vehicle development and customer experience?
Zonal/software-defined architectures reduce the number of ECUs and supplier islands, enabling fast OTA updates (Rivian does monthly updates) and coordinated cross-domain features; this accelerates product improvement and customer engagement.