> Markdown version of [/jobs/ext/3758986-staff-software-development-engineer-it-infrastructure-engineering](https://www.wearedevelopers.com/jobs/ext/3758986-staff-software-development-engineer-it-infrastructure-engineering). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Staff Software Development Engineer, IT Infrastructure Engineering

- **Company:** Tesla, Inc.
- **Location:** Austin, TX, United States
- **Experience:** Experienced
- **Contract:** Permanent contract
- **Skills:** Application Programming Interfaces (APIs), Audit Trail, Code Review, Computer Engineering, Python (Programming Language), Software Engineering, TypeScript, Web Applications, ReactJS, Large Language Models, Backend, Kubernetes, Information Technology, Front End Software Development, Invoking Functions, Human in the Loop, Docker
- **Published:** October 15, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=14d6958dce276bd6

## About the Role

* At least 3-5 years of experience with bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, Mathematics, Physics or equivalent experience
 * Hands-on experience building LLM agents that use tools (function calling, MCP, or equivalent): routing, context, evaluation, and making the system more reliable over time. This is the screen, must have examples running in production
 * Strong Python, including services and APIs, and the ability to work in an existing agent template and production codebase
 * Experience shipping production software that other people depend on: design, implementation, code review, testing, observability, and operating what you ship
 * Good judgment around blast radius. You have thought about what happens when an automated system is wrong, and you default to propose-then-apply, audit logs, and fail-safe behavior rather than unsupervised writes
 * Ability to work with non-software partners (network and control engineers, technicians, operators). You can turn complex operational workflows into software without needing a product manager to translate
 * Comfortable sustaining a modern web stack (Python/TypeScript/React and APIs) as needed. Deep frontend specialization is not the job
 * Experience with Docker and Kubernetes, or a clear ability to get there quickly, since this software runs in that environment
 * Familiar with latest SI tools and workflows for software development
 * Modern MCP/SI Agent Security, including OBO authentication and authorization

## Description

At the core of the job there is an SI agent platform you will help build: an orchestrator on Tesla's agentic stack, connected to internal tools and data sources, that can answer questions, audit configurations, troubleshoot issues, and propose fixes with a human in the loop. You will also improve our existing web app and backend services, including self-service onboarding, alerting/notifications.
What You'll Do

 * Own the agent platform end to end: architecture, implementation, evaluation, and rollout on Tesla's agent stack, starting from the existing prototype and taking it to something our team and field engineers use in their daily work
 * Connect the orchestrator to internal systems through tools and MCP-style integrations (fleet management, logs and telemetry, ticketing, and NOC workflows) and add new data sources as our customers' needs grow
 * Design human-in-the-loop actions: the agent investigates, explains, and proposes a change; a user approves before anything is applied. Build the audit trail, guardrails, and failure handling that this requires. When sources disagree, the agent asks the user rather than guessing
 * Build automations that eliminate manual work around our IT Infra workflows. Your work will cut down on commissioning time, helping us build factories faster
 * Sustain the existing web app for fleet visibility, health of applications on the connectivity layer, and onboarding, in partnership with the team: ship the capabilities operators need, keep the system reliable, and avoid turning every request into a one-off
 * Support third party software deployments on Kubernetes for our on-prem fleet-management software (containers, Helm, cluster operations)
 * Work directly with our team and field engineers as the first users. Turn their operational pain into product behavior, then iterate until the tool deletes the manual work
 * Scale automated Private 5G eSIM management services across key sites. You will do software engineering work and own the entire lifecycle of eSIM including provisioning, monitoring and de-provisioning with an emphasis on security