Software Engineer, Foundation Inference Infrastructure

Job Description

As a Software Engineer on the Inference Infrastructure team at Tesla, you will be responsible for designing and implementing backend services and tools that power autonomy software and processes.

Requirements

• Proficiency with Python
• Familiarity with managing hardware inference chips like TPUs
• Familiarity with optimizing machine learning inference workloads for low latency and scale
• Experience with Linux, container orchestrator like Kubernetes, and bare metal setup tools like Ansible
• Experience with data stores like PostgreSQL and Redis

Responsibilities

• Design and implement backend services and tooling for iteration and batch processing of inference, simulation, and evaluation workloads
• Collaborate with Autonomy teams to build foundational components and bridge missing pieces in ML compiler and runtime infrastructure
• Design for scalability, reliability, security, and high performance

Benefits

• Employees at Tesla are often offered day-one coverage with multiple medical options (some at $0 paycheck cost), dental/vision, company HSA contributions, a 401(k) match, and equity programs. Most roles also include paid time off and holidays, family-building support, employee assistance, commuter and childcare benefits, and access to discounts and wellness programs.