Hedra
Senior/Staff Software Engineer, Distributed Systems
$175K–$275K
San Francisco · Staff · Full-time · Posted May 21, 2026
- Experience
- 5+ years of software engineering experience.
About the job
Build and operate distributed production systems that schedule, route, and serve compute-intensive workloads for Hedra’s inference platform.
What you'll do
- Design, build, and operate reliable distributed inference infrastructure, including compute scheduling and routing.
- Improve throughput, latency, reliability, and resource utilization; own production operations and incident response.
- Drive architectural decisions and solutions across infrastructure, model serving, APIs, and developer-facing systems.
What they ask for
- 5+ years of software engineering experience, including significant experience building distributed backend or infrastructure systems.
- Track record designing and operating high-availability production services at meaningful scale; strong distributed systems fundamentals.
- Experience debugging complex production systems and with CI/CD, testing and validation, monitoring, alerting, and production operations.
- Strong programming fundamentals, systems-oriented backend language experience, and experience using agentic coding tools and workflows beyond basic prompting.
Nice to have
- Experience with inference or model-serving infrastructure, GPU or accelerator infrastructure, compute scheduling, orchestration, or resource management.
- Experience with Kubernetes or other cluster orchestration systems, performance optimization, platform engineering, or cloud and/or bare-metal infrastructure.
Pay
$175K – $275K (USD, base salary)
Tools
Python, Kubernetes, CI/CD
AI focus
Build infrastructure for model inference and serving; use agentic coding workflows to design, build, debug, and ship software.
Model-written summary · the original posting is authoritative