SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Checkmarx is the leader in application security, serving over 1,800 customers including 40% of Fortune 100 companies. The company's consolidated platform helps enterprises secure application development from code to cloud, addressing the needs of AppSec teams, developers, and CISOs.
You will join one of the R&D teams building the AI-driven core of the product. This role combines hands-on engineering with strategic technology evaluation. You'll design and own LLM-powered pipelines and agent-based systems that find, triage, and remediate security risk in production at scale. You'll design retrieval and context strategies (RAG, tool use, memory) that ground model behavior in the product's data and domain.
Key responsibilities include defining and running evaluations for model and agent quality to drive iteration and model selection; evaluating emerging AI tools, models, and frameworks against product needs and producing clear build-vs-buy-vs-integrate recommendations for the team and leadership; staying ahead of the AI landscape by tracking new LLM releases, agent architectures, orchestration frameworks, and techniques, then translating relevant developments into concrete engineering proposals; owning the reliability of AI features in production through guardrails, structured output validation, fallback behavior, and observability tuned for LLM-based systems; and participating in design discussions and code reviews, bringing an AI-informed perspective to architecture decisions.
The tech stack centers on cloud-native architecture in Go. The specific product area may evolve with roadmap priorities, but the core of the job remains constant: AI-driven features, applied judgment about the AI tooling landscape, and production-grade systems engineering.
Requirements: Not explicitly stated in the provided posting text.
