About the job
About Semgrep
Semgrep is a pioneering force in code security, enabling developers to innovate seamlessly. Our platform empowers teams to identify, flag, and remediate genuine security issues before deployment, leveraging an adaptive security framework that evolves as you build. Semgrep safeguards code in real-time, providing essential guardrails that allow developers to work swiftly while maintaining security. Trusted by security professionals, Semgrep integrates into developers' workflows, delivering solutions without disrupting productivity and providing security teams with critical visibility, control, and assurance. Our AI learns from your coding context, effectively reducing false positives and highlighting actionable vulnerabilities, as validated by 95% of security reviewers across over 6 million findings. With Semgrep, achieving zero false positives is attainable, as our AppSec teams experience an 80% reduction in false positives across both Code and Supply Chain, significantly alleviating workload.
Founded in the heart of San Francisco and supported by esteemed investors including Menlo Ventures, Felicis Ventures, Lightspeed Venture Partners, Redpoint Ventures, and Sequoia Capital, Semgrep has been recognized by Gartner in Application Security Testing. We are proud to serve leading organizations such as Snowflake, Dropbox, and Figma. Discover more about us at semgrep.dev.
About the Role
As a Senior AI Software Engineer, you will leverage large language model (LLM) technologies to enhance Semgrep's capabilities in detecting, prioritizing, and remediating security vulnerabilities. You will engage directly with clients to comprehend their challenges, oversee the comprehensive implementation of AI-driven solutions, and meticulously assess the effectiveness of various models and prompts through hands-on experimentation with real-world data. If you thrive in dynamic environments, enjoy rapid prototyping, and are eager to contribute across multiple aspects of our technology stack, this role is an excellent fit for you.
Our technology stack incorporates various LLMs, including GPT-4/GPT-5, Codex, and Claude, alongside Typescript and React for the front end, and Python, Flask, and SQLAlchemy for the back end. Our deployments are managed via Kubernetes and hosted on AWS. While professional experience with these technologies is advantageous, a willingness to learn them quickly is sufficient!
This is a hybrid position, requiring you to join us in our San Francisco, New York, Boston, or Denver offices three or more days a week, depending on your team. Remote work may be considered for exceptional candidates.

