Software Engineer - Infrastructure
You will develop and maintain API layers and backend services for the Targon ecosystem. You will build systems that orchestrate confidential workloads across distributed GPU networks, including attestation and scheduling paths for TVM and TargonOS. You will benchmark services, identify bottlenecks, improve performance and reliability, operate resilient infrastructure, and create new services and applications from scratch.
Responsibilities
- Develop and maintain API layers and backend services
- Build and scale systems that orchestrate confidential workloads across distributed GPU networks
- Benchmark services to identify bottlenecks
- Improve performance and reliability
- Design and operate resilient, observable infrastructure
- Create new services and applications from scratch
Requirements
- Proficiency with Golang for backend development
- Experience working with Kubernetes in production
- Familiarity with Python for scripting and tooling
- Strong background with Unix/Linux systems
- Experience with distributed systems, networking, or high-throughput service design
- Exposure to confidential computing, TEEs, or secure infrastructure
- Ownership and ability to drive ambiguous problems to shipped, well-tested solutions
- Experience optimizing database performance and designing scalable architectures
- Experience with AI/ML inference, training, GPUs, or model deployment
- Experience working on permissionless systems or building market-related products
- Familiarity with GitHub, Discord, Notion, and Linear
Benefits
- 401K matching
- Unlimited paid time off (PTO)
- Fully covered health insurance
- Fully covered dental insurance
- Fully covered vision insurance
- 24/7 Employee Assistance Program (EAP)