Staff Software Engineer: Secure Execution & AI Sandbox

harvey; San Francisco (CA); On-site; USD 231,000 - 346,000; Full time

Job summary

Harvey is building a scalable security engineering platform for AI agents. You’ll lead development of execution environments, containment, and protections across product sandbox and internal AI platforms.

The role emphasizes security, reliability, and performance, with ownership from design to production operation. Join a founding team shaping next-gen security for agent-based workflows.

Qualifications

• 10+ years developing and running production software.
• Strong software engineering in Go, Rust, Python, or C++.
• Deep expertise in sandboxing, OS isolation, container security, or untrusted-code platforms.
• Experience building shared platforms and enabling teams via clear interfaces.
• Experience with cloud infrastructure and distributed systems.
• Fluency with AI-assisted engineering and agentic workflows.
• Strong communication and technical judgment.

Responsibilities

• Set the technical direction for secure agent execution across Security, Infra, and Product Eng.
• Design, build, and operate a platform for security agents to discover and validate vulnerabilities.
• Build reusable controls for agent tool use, code execution, network and data access.
• Partner with Harvey’s product sandbox and agent platform to implement protections.
• Enable internal use of open-source models with protections around data handling.
• Develop adversarial tests and telemetry to verify containment and expose failures.
• Lead delivery across teams and mentor engineers through production rollouts.

Skills

Go

Rust

Python

C++

Linux

Networking

Containers

Cloud infra

Observability

AI workflows

Security

Communication

Tools

Firecracker

gVisor

Kata Containers

Namespaces

Seccomp

Landlock

Job description

Harvey is building a scalable security engineering platform for AI agents. You’ll lead development of execution environments, containment, and protections across product sandbox and internal AI platforms.

The role emphasizes security, reliability, and performance, with ownership from design to production operation. Join a founding team shaping next-gen security for agent-based workflows.