Software Engineer, Agentic Tooling

Tesla offers a benefits-forward role in Palo Alto, onsite, with a focus on the harness and skill ecosystem that powers our AI org behind FSD and Optimus. You will help extend the agent runtime, ship practical skills, and maintain robust evaluation, observability, and production infrastructure, all while collaborating across teams to turn complex workflows into reliable tooling.

Benefits

• Medical plans with plan options and $0 payroll deduction
• Family-building, fertility, adoption and surrogacy benefits
• Dental and vision plans, including orthodontic coverage, with $0 paycheck contributions
• Company funded Health Savings Account contributions when enrolled in the high-deductible plan with HSA
• Healthcare and Dependent Care Flexible Spending Accounts (FSA)
• 401(k) with employer match, Employee Stock Purchase Plans, and additional financial benefits
• Company paid Basic Life and AD&D insurance
• Short-term and long-term disability insurance (90 day waiting period)
• Employee Assistance Program
• Sick and vacation time, flex time for salary roles, accrued hours for hourly roles, and paid holidays
• Back-up childcare and parenting support resources
• Voluntary benefits including critical illness, hospital indemnity, accident insurance, theft & legal services, and pet insurance
• Weight loss and tobacco cessation programs
• Tesla Babies program
• Commuter benefits
• Employee discounts and perks program

Responsibilities

• Extend the agent runtime and tool ecosystem end to end, adding new tools, integrations, and backends without regressing existing skills while keeping the platform easy to extend as the ecosystem grows
• Ship new skills that streamline real workflows for engineers across the AI org, from one-off automations to reusable agent capabilities used across the fleet
• Design and operate the evaluation framework to catch regressions in prompts, skills, harness changes, and model upgrades before they reach users
• Own session-level observability across tracing, logging, and metrics; build dashboards and alerts that flag issues before users are affected
• Operate production agent services on Kubernetes, async backend services, durable storage for session memory and embeddings, and the public-facing APIs that route work to them
• Contribute to architectural decisions with a focus on security, scalability, and reliability, particularly around credential isolation and the interfaces between harness, model runtime, and the sandboxing layer
• Embed with users and ship cross-team, end-to-end solutions: collaborate with engineers across the AI org to understand workflows, identify toil moments, and drive solutions from initial conversations through prototype, rollout, and hand-off

Requirements

• Proficiency with Python; Go is a plus
• Strong foundation in Linux systems; containerization and Kubernetes experience is a plus
• Solid background in concurrent and asynchronous programming
• Experience with relational and vector data stores to support long-running agent workflows is a plus
• Open-ended problems and product instincts: ability to translate vague asks into end-to-end shipped solutions with a usable first version
• Adaptability and curiosity in a fast-paced space: weekly developments in agent tooling; stay current on models, frameworks, and agent patterns and re-platform when needed
• Experience with Claude Code SDK, ACP (Agent Client Protocol), or opencode is a plus
• Experience with sandboxing, application security, sandboxed code execution, container isolation, capability-based access control, credential isolation, and secrets management is a plus
• Experience building or operating an evaluation pipeline for skills, prompts, or models, including offline replay, scoring against ground truth, or regression gating in CI, is a plus
• Experience with CI/CD for ML or agent systems, distributed task orchestration, or developer-tools work where the customer is another engineer is a plus

Technologies

• Python
• Go
• Linux
• Kubernetes
• Claude Code SDK
• ACP (Agent Client Protocol)
• opencode

Compensation

Expected compensation: USD 140,000 to 390,000 per year in base salary, plus cash and stock awards and benefits. Pay offered may vary based on location, knowledge, skills, and experience. The total compensation package may include additional elements dependent on the position. Details of participation in benefit plans will be provided if an offer is made.