Staff+ Software Engineer, ML Inference Path

About the role

Anthropic is looking for a Staff+ Software Engineer to join the Safeguards ML Inference Path team. You will help design, build, and operate the production infrastructure that powers Claude’s safety systems, working at the intersection of machine learning, large‑scale distributed systems, and AI safety.

Key responsibilities

• Design and implement scalable ML infrastructure for real‑time safety deployments across classifiers and models.
• Develop monitoring and observability tools to track classifier performance, data quality, and system health.
• Partner with research teams to translate safety research into robust production systems.
• Optimize inference latency and throughput while maintaining high reliability.
• Build automated testing, deployment, and rollback pipelines for safety‑critical ML models.
• Collaborate with Safeguards, Security, and Alignment teams to meet safety and production requirements.

Required profile

• Strong experience productionizing ML systems and handling high‑throughput, low‑latency workloads.
• Proven ability to create self‑service deployment pipelines and evaluation infrastructure.
• Experience building A/B testing or experimentation frameworks for ML.
• Results‑oriented mindset with a focus on reliability in safety‑critical environments.

Required skills

• Python programming
• ML frameworks such as PyTorch, TensorFlow, or JAX
• Distributed systems principles
• Automated deployment pipelines
• A/B testing and experimentation infrastructure