About the Role
As a Backend Software Engineer at tensormesh, you’ll help build the systems that power large-scale, high-performance LLM inference. You’ll design, optimize, and scale core backend components that support caching, orchestration, and observability across multi-cloud environments.
What you’ll do
- Design and implement distributed systems for high-throughput, low-latency inference workloads
- Build and evolve APIs and services supporting LMCache, vLLM, and multi-cloud GPU orchestration
- Develop pipelines for tracking, storing, and analyzing model performance and usage data
- Integrate with major model providers and frameworks to improve interoperability and efficiency
- Collaborate with product and research teams to deliver new platform capabilities end-to-end
Ideal candidate credentials
- 5+ years of backend engineering experience building distributed or high-scale systems
- Strong background in performance optimization, data integrity, and system reliability
- Proficient in backend technologies like Go, Python, Rust, Postgres, Redis, and Docker (AWS/GCP a plus)
- Familiarity with observability and monitoring tools (Prometheus, Grafana, Datadog, etc.)
- Clear communicator and team player who documents well and ships quickly
Benefits include
Medical, dental, and vision insurance
401k plan
Daily lunch, snacks, and beverages
Flexible time off
Competitive salary and equity
Equal opportunity
Tensormesh is an equal opportunity employer. All applicants will be considered without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran, or disability status.
