Staff ML Inference Infra Engineer (Safety)

FDE Times; San Francisco (CA); Ibrido; USD 320.000 - 485.000; Tempo pieno

Descrizione del lavoro

Anthropic is seeking engineers to design and operate production ML infrastructure powering Claude's safety systems. You will work where ML, distributed systems, and AI safety meet, delivering scalable tooling used in every model launch across multiple platforms.

The role emphasizes building reliable, low-latency inference with automated testing and deployment processes, collaborating with researchers to translate safety research into robust production systems.

Competenze

• Proficient in Python and ML frameworks; production experience.
• Experience building scalable ML infrastructure for real-time safety deployments.

Mansioni

• Design scalable ML infrastructure for real-time safety deployments across classifier and model ecosystem.
• Build monitoring and observability tools for classifier performance, data quality, and system health.
• Collaborate with research teams to productionize safety research into robust systems.
• Optimize inference latency and throughput for real-time safety evaluations.
• Implement automated testing, deployment, and rollback systems for ML models in production safety apps.
• Partner with Safeguards, Security, and Alignment teams to meet safety and production needs.

Conoscenze

Python

ML frameworks

Distributed systems

Deployment pipelines

A/B testing

Reliability

Formazione

Bachelor's degree

Strumenti

PyTorch

TensorFlow

JAX

Descrizione del lavoro

Anthropic is seeking engineers to design and operate production ML infrastructure powering Claude's safety systems. You will work where ML, distributed systems, and AI safety meet, delivering scalable tooling used in every model launch across multiple platforms.

The role emphasizes building reliable, low-latency inference with automated testing and deployment processes, collaborating with researchers to translate safety research into robust production systems.