Member of Technical Staff, Product Security

Inferact•San Francisco, CA

5d•$200,000 - $400,000

About The Position

Inferact is seeking a Member of Technical Staff, Product Security to secure its product as it moves from early deployments to production use by enterprise customers. The role owns security across the inference platform and its APIs, the control plane, cloud and Kubernetes infrastructure, and the software build and release process. This is a hands-on engineering role. The successful candidate will threat-model features with engineering teams, review and write production code, find and fix vulnerabilities, and build secure defaults, tooling, and guardrails. They will collaborate with inference, infrastructure, product, and forward-deployed engineering teams, as well as the engineer responsible for vLLM vulnerability management when upstream issues affect the product. The role sets the direction for product security and carries work from design review through shipped fixes.

Requirements

Hands-on product or application security experience on software customers run or depend on, with a record of finding, fixing, and preventing real vulnerabilities.
Strong software engineering ability, including reading and writing production code, reviewing pull requests, and shipping fixes with tests.
Experience threat-modeling and reviewing distributed systems, APIs, and services, including authentication, authorization, multi-tenancy, data isolation, and secrets handling.
Working knowledge of cloud and container security, including IAM, network boundaries, Kubernetes, and infrastructure as code.
Sound risk judgment, including distinguishing reachable risks from theoretical ones and choosing controls appropriate to the company's stage.
Clear written and verbal communication with engineers, leadership, and customer security teams, and discretion with sensitive information.

Nice To Haves

Experience securing AI/ML infrastructure, model serving, GPU workloads, or developer platforms.
Experience securing software supply chains and CI/CD, including dependency risk, build integrity, artifact signing, and container image hardening.
Familiarity with inference-system security risks, including untrusted model loading, tenant isolation on shared hardware, and handling prompts and outputs.
Experience building security tooling, paved roads, or secure-by-default libraries that engineers adopt.
Experience answering technical questions in enterprise customer security reviews and supporting customer deployments in their own cloud environments.
Credited CVEs, security fixes, or security tooling in widely used open-source infrastructure.
Experience building a product security function from the ground up at an early-stage company.
Offensive security or security research experience translated into lasting engineering fixes.
Contributions to vLLM, PyTorch, or other inference and ML infrastructure projects.

Responsibilities

Own security for the inference platform and its APIs, control plane, cloud and Kubernetes infrastructure, and software build and release process.
Threat-model new features with the engineers building them and review system designs.
Read, write, and review production code; find and fix vulnerabilities and provide tests for fixes.
Build secure defaults, security tooling, and guardrails that help engineers work safely.
Collaborate with inference, infrastructure, product, and forward-deployed engineering teams.
Coordinate with the engineer who owns vLLM vulnerability management when upstream issues affect the product.
Set the direction for product security and take security work from design review through delivery of a fix.