Member of Technical Staff, AI Infrastructure Reliability
Fireworks AI · San Mateo · New York
CHECKED 1H AGO
Infrastructureremotesenior$200k–$290k
At a glance
Highlights
- Keep platform serving 40T tokens daily dependable as it grows.
- Define reliability bar with SLOs, error budgets and readiness.
- Own incident management, postmortems and self-healing automation.
What they offer
- Equity
Ideal candidate
A systems-minded owner who thrives on hard infrastructure problems, digs across unfamiliar stacks, and earns adoption through useful tooling to keep large-scale AI dependable.
Requirements
- 5+ years with Linux internals, performance troubleshooting and networking (TCP/IP, HTTP, gRPC)
- 5+ years writing production-grade tools and systems code in Python, Go, C++ or Rust
- Experience operating and debugging Kubernetes, Terraform and Docker in high-throughput production
- Experience with distributed systems such as high-throughput control planes, microservices or multi-region setups
- Background in fault-tolerant design, SLO/SLA management, automated failover and HA architecture
- Bachelor's or Master's in Computer Science, Computer Engineering or equivalent experience
Lab profile
About Fireworks AI
Platform for specialized intelligence to build, train, and serve tailored AI models.
What they build
- Platform to build, train, and serve tailored AI models
- Hundreds of open models for production AI
- Text, image, embedding, audio, and multimodal models
Known for
- Founded by team behind PyTorch
- Specialized intelligence tailored to customer data and workflows
- Production-grade AI for text, image, audio, and multimodal workloads
Key facts
- Backed by AMD, NVIDIA, Sequoia Capital, Benchmark Capital, Index Ventures, Lightspeed, TCV, and Atreides