Staff Software Engineer, Secure Execution

San Francisco · USD 231,000-346,400 · 10+ years experience · Full-time · Hybrid · Posted Sep 30, 2026

At a glance

As a Staff Software Engineer on the Security Engineering team, you will join as a founding team member to build the security foundations for Harvey's AI agents.
You will lead the development of a platform for agents to perform security work while shaping how agents are sandboxed across product and internal platforms.
The role involves balancing containment with reliability, performance, and flexibility while enabling models to perform tasks like vulnerability discovery and validation.

Set the technical direction for secure agent execution across Security, Infrastructure, and Product Engineering.
Design, build, and operate a platform for security agents to discover and validate vulnerabilities within authorized targets.
Build reusable controls for agent tool use, code execution, network and filesystem access, and workload lifecycle.
Integrate with identity and secrets platforms to limit access to data and credentials.
Partner with product sandbox and internal agent platform owners to implement protections and integrate security capabilities.
Enable internal use of open-source models by building protections around model serving and sensitive-data handling.
Develop adversarial tests, evaluations, and telemetry to verify containment and expose failures.
Build mechanisms to scope, observe, interrupt, and safely terminate agent activity.
Lead delivery and adoption across teams while mentoring engineers.
Remain hands-on through implementation and production operation, balancing security, reliability, latency, and cost.

10+ years developing and running production software, including technical leadership on initiatives spanning multiple engineering teams.
Strong software engineering skills in languages such as Go, Rust, Python, or C++.
Practical experience in Linux systems, networking, and containerized infrastructure.
Deep expertise in execution security, such as sandboxing, operating-system isolation, container or virtual-machine security, or platforms that execute untrusted code.
Experience building shared platforms, services, or libraries and helping other teams adopt them.
Experience with cloud infrastructure and distributed systems, including observability, failure handling, and capacity management.
Fluency with AI-assisted engineering and agentic workflows.
Strong communication and technical judgment with a record of bringing teams to agreement on ambiguous problems.

Experience with microVMs, hypervisors, or sandbox runtimes such as Firecracker, gVisor, or Kata Containers.
Experience with Linux isolation mechanisms such as namespaces, seccomp, and Landlock.
Experience building agent runtimes or tool-execution frameworks.
Experience with automated security-testing platforms.
Experience with vulnerability research, penetration testing, or adversarial evaluation of agent systems.
Experience deploying or securing self-hosted inference and open-source models.
Experience with isolation of model-serving workloads and protection of sensitive inputs and outputs.