AI Product Engineer, Code

About the role

As an AI product engineer on Semgrep’s Code team, you’ll apply cutting-edge AI/ML tools from industry leaders to build user-facing security tools that help developers write and ship secure software faster.

Semgrep’s Code product improves the software developers create by identifying real vulnerabilities without slowing them down. Other security tools often overwhelm developers with noise, but we deliver actionable, accurate, and intuitive results. AI has already had a profound effect on how we can cut through that noise, and we believe it will unlock even more potential in the future.

You’ll learn about the application-security space, mentor other engineers, collaborate with product managers, security researchers, and application developers, and shape features our customers love. Through Semgrep’s culture of transparency, you’ll see and influence the decisions that make a startup successful. Your work will be key to making Semgrep the world’s leading code analysis project and trusted security platform.

• Integrate AI platform APIs into the Code product
• Develop and refine LLM prompt chains for real developer use cases
• Experiment with the latest AI/ML advances and determine how they can be productized
• Evaluate and fine-tune ML models using human- and machine-generated data
• Learn directly from users to understand their needs and deliver features that help them secure their code
• Work on major product initiatives end-to-end, from design and prototyping through implementation and deployment
• Contribute to technical discussions, roadmap planning, and mentoring within the team

• 8+ years of experience writing production software
• Curiosity and a love of new technologies, especially AI/ML
• Experience experimenting with GPT-4/GPT-5, Codex, Claude, or other LLMs; familiarity with ML algorithms and applied research
• Comfort working in a fast-paced environment where prototypes are rapidly iterated or discarded
• Strong Python skills (experience with other languages a plus)
• Interest in prompt engineering, embeddings, and vector databases
• Excitement about building for customers, iterating fast, and seeing solutions solve real developer problems
• Excellent and proactive communication skills, both verbal and written

• Building new detection capabilities that utilize fast, deterministic static analysis technologies within an autonomous LLM-driven agentic code analysis pipeline
• Identifying causes of and solving for non-determinism in model output
• Generating real-time, AI-powered remediation guidance for vulnerabilities in developers’ own code
• Automatically drafting secure code suggestions that align with project context and frameworks
• Building and orchestrating purpose-built custom agents for evaluating and triaging code security risks
• Enhancing the IDE experience with AI-assisted security insights and explanations
• Experimenting with AI-powered rule generation to help customers expand and tailor their Code product usage

Salary Range : $202,000 - $238,000

Our compensation package includes equity and benefits in addition to salary.

Please note that the range listed is for someone based in the San Francisco Bay Area.

Our goal is to competitively and fairly compensate every Semgrep employee with a system that equally rewards those who are vocal and those who are less comfortable making demands during the final steps of the hiring process. To that end, we generate internal compensation bands that are used when discussing and negotiating salaries. We update these based on market data to make sure they’re above the average for comparable roles.

We also invest in our employees’ well-being and long term success with comprehensive health plans, generous vacation time, 401k, learning stipends, and more. Our benefits are for everyone, so that you’re taken care of, and we work with individuals to make sure they have what they need, whether that’s quiet work space, adjusted hours, or something else.

We have people from France and the Philippines, physics and philosophy, formal methods research and full fledged…