Performance Engineer Inference Systems
1 month agoSalary: 350K - 850KSan Francisco, CA | New York City, NY | Seattle, WAHybridEngineeringJobs by Anthropic
AnthropicVisit Anthropic website
AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.
San Francisco, United States
Funding history
About Anthropic
Anthropic PBC develops frontier AI systems and deploys them through Claude products and the Claude Platform, with a stated focus on safety, interpretability, and steerability.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will investigate performance, reliability, and correctness across the inference stack. You will build observability and modeling tools, improve output-correctness evaluations, identify high-impact optimization opportunities, and partner with component owners to deliver improvements.
Requirements
- Performance engineering
- Profiling
- Roofline analysis
- Latency optimization
- Throughput optimization
- Root-cause investigation
- Python
- SQL
- Pandas
- Data analysis
- Numerics
- Evaluation design
- Regression detection
Responsibilities
- Investigate throughput, latency, and reliability issues across the inference stack
- Improve the correctness evaluation pipeline across hardware platforms and serving configurations
- Build observability, dashboards, and modeling tools
- Partner with kernel, serving, routing, autoscaling, and capacity teams on optimizations
- Prioritize opportunities by impact and effort
Benefits
- Equity donation matching
- Generous vacation
- Parental leave
- Flexible working hours