Senior / Staff+ Software Engineer - Autonomous Agent Infrastructure
Staff+ engineer building the agentic infrastructure layer for claude.ai: sandboxed execution, stateful task orchestration, and secure delegated access at scale.
About the job
Key Responsibilities
- Design and build sandboxed compute environments where Claude can safely execute code, access tools, and interact with external services
- Build state management systems for long-running agent tasks, handling checkpoints, recovery, and resumption across failures
- Develop authentication and authorization frameworks for delegated access, so Claude can act on behalf of users securely
- Create observability and debugging tools for agent execution, so we understand what Claude did, why, and how to make it better
- Partner closely with product and research teams to define what's possible and ship it
Minimum Qualifications
- Experience building distributed systems, infrastructure, or platform services at scale
- Comfort building cloud native infrastructure on GCP, AWS, or Azure
- Experience with containers, sandboxing, or secure execution environments (e.g., gVisor, Firecracker, V8 isolates)
- Write clean, maintainable code in Python, Go, Rust, or a similar language
- Care about security, isolation, and building systems that fail safely
Preferred Qualifications
- Comfort with ambiguity and greenfield work where you help shape the architecture
- Interest in problems that don't have existing playbooks
- Experience building multi-tenant execution platforms or serverless infrastructure
- Background in security engineering, sandboxing, or isolation technologies
- Familiarity with workflow orchestration systems (Temporal, Airflow, Step Functions)
- Experience with state machines, checkpointing, or durable execution patterns
- Low-level systems experience (Linux internals, eBPF, container runtimes)
Skills
Python, Go, Rust, GCP, AWS, Azure, Gvisor, Firecracker, V8 Isolates, Temporal, Airflow, Step Functions, Ebpf, Linux Internals, Container Runtimes
Similar jobs
Backend Engineering jobs
Anthropic
San Francisco, CA
Design and operate high-QPS backend systems on Claude’s token-generation path, owning latency, reliability, safe deployments, and incident response. The role requires 8+ years of software engineering experience, strong distributed-systems expertise, and production ownership of mission-critical services.
Anthropic
San Francisco, CABuild and scale distributed inference infrastructure serving Claude across accelerators and cloud providers. The role requires substantial software engineering experience, with expertise in large-scale systems, routing, orchestration, and production machine learning infrastructure.
Earnin
Mountain View, CA
This Senior Staff Software Engineer will define and lead the architecture of EarnIn’s Identity & Trust platform, spanning authentication, authorization, verification, privacy, fraud prevention, and secure data processing. The role requires 8+ years of software engineering experience and deep expertise in secure distributed backend systems.
Coinbase
United States
Sets architectural direction and remains hands-on in building ultra-low-latency institutional trading systems spanning matching, risk, order management, and market data. Requires 10+ years of software engineering experience and deep expertise in distributed systems and backend performance.
Vanta
Remote
Leads architecture and technical strategy for Vanta’s government compliance product, building scalable backend systems and new workflows in a 0-to-1 environment. Requires 10+ years of backend experience, strong systems thinking, cross-functional influence, and a track record of mentoring engineers.