12 hours ago
Base Salary
$231k - $346k/yr
Responsibilities
- Set the technical direction and roadmap for secure agent execution across Security, Infrastructure, and Product Engineering.
- Design, build, and operate platforms that allow security agents to discover and validate vulnerabilities within authorized execution boundaries.
- Build reusable controls for agent tool use, code execution, network and filesystem access, resource consumption, workload lifecycle, identity, secrets, and data access.
- Partner with product sandbox and internal agent platform owners to make architectural decisions and integrate shared security capabilities.
- Enable secure internal use of open-source models by protecting model serving, agent execution, and sensitive data.
- Develop adversarial tests, evaluations, telemetry, interruption controls, and safe termination mechanisms for agent activity.
- Lead delivery and adoption across teams, mentor engineers, and remain hands-on through implementation and production operation.
Requirements
- 10+ years developing and running production software, including technical leadership across initiatives spanning multiple engineering teams.
- Strong software engineering skills in Go, Rust, Python, or C++, with 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 translating threats into enforceable boundaries and testing how those boundaries fail.
- Experience building shared platforms, services, or libraries and supporting adoption through interfaces, documentation, and safe migrations.
- Experience with cloud infrastructure and distributed systems, including observability, failure handling, capacity management, and dependable production operation.
- Fluency with AI-assisted engineering and agentic workflows, including evaluating risks from tool use, code execution, and sensitive-data access.
- Strong communication and technical judgment, with experience aligning teams on ambiguous problems and delivering decisions.
- Preferred experience with microVMs, hypervisors, sandbox runtimes, Linux isolation mechanisms, agent runtimes, tool-execution frameworks, automated security testing, vulnerability research, penetration testing, adversarial agent evaluation, or securing self-hosted inference and open-source models.
About Harvey
Harvey builds domain-specific generative AI for legal and other professional services, delivered as an enterprise platform and APIs to automate contract analysis, due diligence, compliance, and litigation workflows. Founded in 2022 and headquartered in San Francisco, it sells to law firms and corporate legal departments on enterprise agreements; investors include Sequoia Capital and OpenAI. Customers include multiple Am Law 100 firms and Fortune 500 companies’ legal teams.