Staff Software Engineer, Secure Execution
Harvey · San Francisco
About this role
## Staff Software Engineer — Secure Execution ### Why Harvey At Harvey, we’re transforming how legal and professional services operate by combining frontier agentic AI, an enterprise-grade platform, and deep domain expertise. This is a rare opportunity to help build a generational company at a true inflection point—strong product-market fit, world-class investor support, and rapid scaling. We move fast, take ownership, and stay close to customers. Our values: **Decisiveness**, **Simplicity**, and **Job’s Not Finished**. ### Role Overview As a **Staff Software Engineer** on the **Security Engineering** team, you’ll join as a founding team member to build the security foundations that enable Harvey’s increasingly capable AI agents to perform security work safely. You’ll lead development of a platform for agents to execute security tasks, including how agents are **sandboxed** across product and internal platforms. A core challenge is enabling models with advanced cybersecurity capabilities to **discover and validate vulnerabilities automatically** (including through **authorized penetration testing**) while protecting sensitive data and systems. You’ll build execution environments, orchestration, and controls—helping enable internal use of **open-source models** with appropriate protections around **inference**, **tool use**, and **data access**. ### What You’ll Do - Set the technical direction for **secure agent execution**, partnering across Security, Infrastructure, and Product Engineering to turn emerging capabilities and risks into a concrete roadmap. - Design, build, and operate a platform for **security agents** to discover and validate vulnerabilities within authorized targets and execution boundaries, producing **reproducible evidence** engineers can act on. - Build reusable controls for agent **tool use**, **code execution**, **network and filesystem access**, **resource consumption**, and **workload lifecycle**. Integrate with identity and secrets platforms to limit access to only what each task needs. - Partner with owners of Harvey’s **product sandbox** and **internal agent platform** to make architectural decisions, implement protections, and integrate shared security capabilities. - Enable internal use of **open-source models** alongside infrastructure teams, building the protections needed for safe inference and execution. *Note: The provided description appears truncated at the end.*
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.