SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 206,500 - 258,100 / annual
Rivian's Applied AI team is building AI products that help engineers across the company design, build, and support electric vehicles. As a Staff AI Software Engineer specializing in agentic applications, you will shape the technical direction for how Rivian integrates AI into its engineering workflows.
You will bring large language models together with enterprise knowledge and tools to build internal applications at scale, starting with core product engineering workflows and expanding across the vehicle development lifecycle. Your focus will be on automating complex workflows, accelerating decision-making, and reducing manual effort.
Key responsibilities include:
**Platform Architecture**: Define and own the agent platform architecture, including orchestration of long-running, multi-step agents, persistent state management, tool integration, permission-aware access to enterprise data, and evaluation infrastructure that gates production releases.
**Technical Direction**: Establish reusable patterns, interfaces, and engineering standards so that capabilities developed for one application can be adopted across the organization.
**Production Quality**: Set the bar for reliability, observability, and evaluation of AI systems. Ensure production applications meet defined quality, latency, and cost targets.
**Hands-On Engineering**: Lead the design and implementation of the most complex components, deliver reference implementations, and resolve critical integration and reliability challenges.
**Technology Strategy**: Evaluate emerging models, frameworks, and tools; lead technical decisions on build versus buy and vendor selection; translate advances into a roadmap with measurable impact.
**Security & Governance**: Partner with Security, Legal, and Compliance to embed authorization, auditability, and data governance into the platform and applications.
**Talent Development**: Raise the engineering bar through design and code reviews, mentoring, and participation in hiring.
You will report to the Sr. Manager, Applied AI for Product Engineering and remain hands-on in the design and implementation of the most critical components.
**Requirements**:
- 8+ years of professional software engineering experience, including technical leadership of complex production systems
- Shipped and operated LLM-based or agentic applications with real users in production, with evidence of measured quality, adoption, and business impact
- Deep understanding of agent system design: orchestration, tool calling, retrieval and grounding, context and memory management, durable execution, verification and evaluation of nondeterministic systems
- Expertise in backend and distributed systems: APIs, asynchronous execution, state management, fault tolerance, and observability at scale
- Expert-level Python and experience deploying services on cloud infrastructure with containers and automated delivery pipelines
- A record of setting technical direction and engineering practices adopted beyond your own team, with demonstrable impact on systems and engineers that depended on them
- Experience integrating with enterprise systems and data under security, privacy, and permission constraints
- Ability to turn ambiguous user needs into practical technical solutions and communicate clearly with engineers, domain experts, and executives
- Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, or a related field, or equivalent practical experience
**Preferred Qualifications**:
- Experience with multi-agent systems that include verification or adversarial checking, persistent state, and recovery or human-approval mechanisms
- Experience with multimodal applications, document or engineering-drawing understanding, vision models, or computer-use agents
- Familiarity with product development tooling: CAD, PLM, simulation, CAE, or physics-informed machine learning
- Experience improving AI systems through failure analysis, feedback loops, model adaptation, or fine-tuning
- Experience building AI infrastructure or capabilities adopted by multiple teams, or forward-deployed experience at an AI lab or agent-infrastructure company
