Sr. Vehicle Modelling Engineer, Applied AI Systems

Rivian and Volkswagen Group Technologies•Irvine, CA

9d•$135,100 - $185,800

About The Position

The Systems Design Reliability Engineering (SDRE) team is building the next generation of AI-assisted, model-driven systems engineering at Rivian VW Group — replacing heavyweight requirements processes with simulation-first design, Digital Twin-based verification and test coverage. We are a small, high-leverage team, and we are looking for an engineer who wants to work at the intersection of AI tooling and physical system modelling. You will develop and operate the AI tooling and Digital Twin infrastructure that underpins SDRE's cross-domain methods — across Vehicle Controls, Infotainment, Communications, and Access. You will own feature(s) end-to-end: from building plant models and co-simulation environments, to deploying LLM-assisted requirement and test pipelines. You will also do real systems engineering — author requirements, perform analyses, design reviews, STPA, and apply SDRE methods hands-on.

Requirements

BS/MS in Electrical, Computer, Mechanical, or Systems Engineering, or related field — or equivalent demonstrated experience through projects.
Strong Python skills — data processing, prototyping AI workflows, automation scripts, or microservices.
Practical experience building LLM applications: RAG pipelines, semantic search, structured reasoning, or agent frameworks.
Systems-minded: able to decompose a physical product into subsystems, behaviors and interfaces — and reason about how they interact.
Comfort iterating quickly from prototype, to production, using modelling in a fast-paced engineering environment.

Nice To Haves

Experience with physical simulation tools: OpenModelica, Simulink, Julia, Modelica, or FMI/FMU-based co-simulation.
Hands-on projects involving physical systems — vehicle dynamics, powertrain, robotics, Baja SAE, Formula SAE, solar car, or similar.
Familiarity with automotive SE artifacts: requirements, test cases, E/E architecture, CAN signals, DBC/ARXML.
Experience with LLM evaluation: precision/recall, hallucination rate, latency, cost — for SE-specific use cases.
GitLab CI/CD experience;
AI portfolio: projects applying LLMs or ML to engineering or technical documentation — even academic or personal projects count.
Fault tree analysis, DFEMA or STPA know-how

Responsibilities

Build and maintain multi-fidelity plant models (FMU-packaged) for vehicle subsystems — powertrain, dynamics, thermal, body — using Python, OpenModelica, Julia, or Simulink.
Develop and run co-simulation environments (FMI-based) that pair vECUs with plant models for three core use cases: Model-to-code, SIL regression tests, and Field issue replay.
Correlate models against real vehicle, dyno, and lab rig and fleet data.
Build LLM pipelines for requirement drafting, test script generation, coverage gap analysis, and root cause analysis over SE artifacts.
Deploy semantic search and RAG over requirements, architecture models, test scripts, using modern LLM app stacks (LangChain, LlamaIndex, or equivalent).
Integrate AI assistants into GitLab and test management systems via APIs, plugins, and CI/CD pipelines.
Build AI analytics tools that correlate requirements, architecture changes, and calibrations with fleet data, field issues and test failures — surfacing similar historical problems and candidate fault paths.
Author requirements and test cases as a practicing systems engineer — applying RequiTest and test-driven SE methods.
Participate in architecture, interface, and safety design reviews across domains.
Document AI-augmented SE process standards and playbooks; help drive adoption across programmes.
Capture process patterns from domain teams and convert them into AI-supported workflows, with human-in-the-loop guardrails.