Staff ML Inference Platform Engineer

Anthropic; San Francisco (CA); Hybrid; USD 320,000 - 485,000; Full time

Benefits offered by this job

Competitive compensation

Equity donation matching (optional)

Generous vacation and parental leave

Flexible working hours

Nice office space

Job summary

Anthropic is seeking an experienced engineer to join the Safeguards ML Inference Path team. You will design, build, and operate the production infrastructure that powers Claude's ML-based safety systems, collaborating with safety researchers and inference engineers to bring new safety technologies to production and scale across platforms.

We work at the intersection of ML, distributed systems, and AI safety, delivering robust tooling used for every model launch, with emphasis on reliability and

Qualifications

• Proficient in Python and ML frameworks with production experience.
• Strong background in distributed systems for real-time ML workloads.
• Experience deploying ML models with automated testing and rollback.
• Ability to collaborate with researchers and translate research into scalable systems.

Responsibilities

• Design and build scalable ML infrastructure for real-time safety deployments.
• Build monitoring and observability tools for classifier performance and data quality.
• Collaborate with research teams to productionize safety research.
• Optimize inference latency and throughput while maintaining reliability.
• Implement automated testing, deployment, and rollback for ML models.
• Partner with Safeguards, Security, and Alignment teams to meet requirements.
• Contribute to internal tools and frameworks to accelerate safety research.

Skills

Python

Distributed systems

CI/CD pipelines

A/B testing

Collaboration with researchers

Education

Bachelor's degree in a relevant field

Tools

PyTorch

TensorFlow

JAX

Monitoring tools

Job description

Anthropic is seeking an experienced engineer to join the Safeguards ML Inference Path team. You will design, build, and operate the production infrastructure that powers Claude's ML-based safety systems, collaborating with safety researchers and inference engineers to bring new safety technologies to production and scale across platforms.

We work at the intersection of ML, distributed systems, and AI safety, delivering robust tooling used for every model launch, with emphasis on reliability and