Staff Software Engineer, Inference Systems at Scale
Anthropic
San Francisco (CA)
On-site
USD 300,000 - 485,000
Full time
14 days+
Get more replies from employers
Send a job-specific resume in minutes.
Start fresh or import an existing resume
Benefits offered by this job
Competitive salary
Flexible working hours
Generous vacation and parental leave
Job summary
A forward-thinking AI company in San Francisco is seeking an experienced software engineer to join their Inference team. The role focuses on building and optimizing systems for AI model deployment, with a strong emphasis on technical excellence and societal impact. Candidates should possess solid software engineering experience, particularly in distributed systems, and be eager to work in a collaborative environment. Competitive salary range of $300,000 to $485,000 USD and hybrid work policy are offered.
Qualifications
Experience with large-scale distributed systems is a plus.
Experience with machine learning systems at scale is a plus.
Experience with load balancing and traffic management is a plus.
Optimizing LLM inference and caching strategies is advantageous.
Responsibilities
Building and maintaining inference systems for AI models.
Designing routing algorithms for request distribution.
Autoscaling compute fleet according to demand.
Managing multi-region deployments and analysis of observability data.
Skills
Software engineering experience
Distributed systems
Flexibility
Impact-oriented
Pair programming
Understanding of machine learning systems
Technical excellence
Concern for societal impacts
Education
Bachelor's degree in a related field
Tools
Kubernetes
Cloud infrastructure (AWS, GCP)
Python
Rust
Job description
A forward-thinking AI company in San Francisco is seeking an experienced software engineer to join their Inference team. The role focuses on building and optimizing systems for AI model deployment, with a strong emphasis on technical excellence and societal impact. Candidates should possess solid software engineering experience, particularly in distributed systems, and be eager to work in a collaborative environment. Competitive salary range of $300,000 to $485,000 USD and hybrid work policy are offered.