# Staff+ Software Engineer, Claude Managed Agents

**Company**: Anthropic
**Location**: San Francisco, CA
**Work arrangement**: hybrid
**Experience**: staff
**Job type**: full-time
**Salary**: $405,000-$485,000 USD
**Category**: Engineering
**Industry**: Technology
**Wikidata**: https://www.wikidata.org/wiki/Q116758847

**Apply**: https://job-boards.greenhouse.io/anthropic/jobs/5395767008?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply
**Canonical**: https://yubhub.co/jobs/job_06813ff3-65a

## Description

## Job Overview

We are seeking experienced backend and distributed systems engineers to join the Agentic Systems team within our Platform organization at Anthropic. The team builds Claude Managed Agents, a hosted platform for creating, running, and scaling production agents on Claude.

## Responsibilities

### Scale the Platform

You'll design and operate systems for long-lived, stateful sessions that execute autonomously, persist through disconnections, and resume cleanly across various environments. This includes durable session and event storage, sandbox orchestration, streaming, scheduling, and multi-tenant isolation. Reliability, latency, and cost efficiency are key product features you'll own in production.

### Evolve the Harness

The harness is the loop that calls Claude, routes tool calls, manages context, and recovers from errors. You'll work with research to revisit harness assumptions with each model generation, build evaluation infrastructure, and ensure the harness gets the most out of Claude.

### Help Builders Get the Most Out of Claude

You'll develop capabilities that enhance what agents can do, such as outcome-driven execution, multi-agent orchestration, memory, and observability. The goal is to deliver the highest intelligence per dollar of any agent platform, safely.

### Design APIs That Outlast Their Implementations

You'll shape primitives like agents, environments, sessions, and event streams, focusing on versioning, ergonomics, and sensible defaults. These APIs will be used by thousands of developers and our own products.

## Requirements

- Minimum of 8 years of practical experience as a backend, distributed systems, or infrastructure engineer

- Experience building and operating stateful, long-running, or high-throughput systems in production

- Strong product sense and API design skills

- Comfortable with 0 → 1 work and navigating ambiguity

- Experience with Claude or other AI tools is a plus

- Take full ownership of your work, from design through build, deployment, and operations

## Nice to Have

- Built or contributed to an agent harness, agent framework, or LLM orchestration layer

- Worked on an AI or ML platform

- Experience with durable execution or workflow engines, sandboxed code execution, or container runtimes

- Shipped public developer platforms, APIs, or SDKs used by external developers at scale

## Logistics

- Annual salary: $405,000 - $485,000 USD

- Location preference: NY, SEA, SF, or the Bay Area

- Hybrid policy: At least 25% of time in one of our offices

- Visa sponsorship available

## Benefits

- Competitive compensation and benefits

- Optional equity donation matching

- Generous vacation and parental leave

- Flexible working hours

- Lovely office space

## Skills

### Required
- backend engineering
- distributed systems
- API design
- cloud computing
- stateful systems
- long-running systems
- high-throughput systems
- reliability engineering
- latency optimization
- cost efficiency

### Nice to have
- agent harness
- LLM orchestration layer
- AI platform
- ML platform
- durable execution
- workflow engines
- sandboxed code execution
- container runtimes
- public developer platforms
- APIs
- SDKs

---

Source: [Apply at job-boards.greenhouse.io](https://job-boards.greenhouse.io/anthropic/jobs/5395767008?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply)