.jpg?1765804504)
Senior AI Engineer
About Sweet Security
Sweet Security is a hyper-growth cloud security startup built on innovation, collaboration, and a shared DNA of excellence. In a world where cloud environments evolve faster than ever, Sweet delivers a groundbreaking Cloud Runtime CNAPP and AI Security capabilities that empowers organizations to detect and stop runtime threats in real time.
We’re transforming how companies protect their cloud environments by combining deep engineering expertise with a fast-moving, team-oriented culture where everyone contributes and everyone wins. Backed by $120M in funding from leading investors - Evolution, Glilot, Greylock, Zscaler, Key1 Capital, and CyberArk, Sweet Security is rapidly expanding as we build the next generation of runtime cloud protection and empower talented people to make a real impact from day one.
Job Description
Sweet Security is seeking a Senior AI Engineer to join a core team delivering advanced AI-driven security solutions that protect our customers’ AI systems.
You will design, build, and productionize LLM-based capabilities and AI agents that enhance real-time threat detection, investigation, and automated response in cloud environments.
Job responsibilities
- Design and develop LLM-powered agents for the Sweet platform.
- Integrate with large volumes of data and external systems (MCP, third-party services, and cloud data sources).
- Build and optimize prompts, RAG pipelines, and agent workflows.
- Develop evaluation datasets and monitoring frameworks for LLM performance.
- Collaborate with engineering and security research teams to deliver scalable AI solutions.
Job requirements
- 7+ years of experience as a Backend Developer.
- 2+ years of experience building production-grade systems, including hands-on generative AI experience - Must
- Strong experience with Python and TypeScript / Node.js.
- Strong understanding of cloud development and containerized environments.
- Experience designing or orchestrating multi-agent systems or agentic workflows.
- Hands-on experience with prompt engineering, RAG, or agent frameworks (LangChain, LangGraph, Bedrock, etc.).
- Background in cloud security — an advantage.
Apply for this job
*
indicates a required field