🤖 AI Engineer / LLM Developer
🚀 About the Role
We're building Keymate, a next-generation access governance platform that extends Keycloak with fine-grained authorization, multi-tenant IAM, and policy intelligence.
As part of this journey, we are hiring an AI Engineer to help us design and implement intelligent capabilities—such as policy suggestion, decision insights, and chat-driven IAM management—powered by modern LLMs and observability data.
This is a hands-on engineering role for someone who’s passionate about LLMs, prompt engineering, embedding-based search, and turning AI ideas into real-world IAM tools.
🧠 What You'll Work On
- Build policy suggestion systems to assist admins in writing and refining authorization rules
- Generate insight and explanation layers for access decisions using OpenTelemetry traces and logs
- Collaborate on chat-based IAM operations using MCP agents integrated with our platform
- Design lightweight NLP pipelines for matching resources, user context, and policies
- Create embedding-based search tools (e.g., vector DB lookup) to explore rules, roles, and access history
- Prototype and productize prompt chains, chat interfaces, and autonomous IAM assistants
- Contribute to our long-term strategy for AI-driven observability and policy management
✅ What We’re Looking For
- Hands-on experience or strong motivation in working with LLMs, RAG, or policy agents
- Familiarity with prompt engineering, vector databases, and semantic search
- Solid development skills in Python and/or Java (our stack: Quarkus backend, React frontend)
- Understanding of IAM or interest in making access control more intelligent and explainable
- Passion for building useful, usable tools—not just demos
- Strong communication and research skills to collaborate with product and security teams
- Bonus: GitHub repos, Colab notebooks, AI course certificates that show your initiative
🌱 Bonus (Not Required, But Helpful Later)
- Exposure to MLOps tools such as MLflow, Triton, or model lifecycle monitoring
- Understanding of model versioning, fine-tuning, or privacy-aware AI in enterprise settings
🤝 What We Offer
- The chance to shape the AI layer of a serious enterprise platform—not just experiments
- Collaboration with backend, security, and observability engineers
- Fully remote, async-friendly work culture
- Support to explore and learn AI technologies that align with real-world security needs
Note: You don’t need to be an AI research expert. We're looking for engineers who love building useful things with AI, understand IAM complexity, and want to make it simpler with smart systems.
Ready to Apply?
We'd love to hear from you! Express yourself freely in an email and tell us why you're excited about this role.
Send your application to:
careers@keymate.ioNote: You can share your resume in whichever medium you express yourself best - whether that's a PDF, portfolio website, GitHub profile, or creative presentation.