Project description
We're looking for an experienced engineer to build and operate a next-generation policy validation and enforcement platform that combines agentic AI capabilities with rule-based controls. This role sits at the intersection of Software Engineering, DevOps, and AI/ML, focusing on scalable, cloud-native solutions that automate governance and compliance validation.
Responsibilities
- Design and develop AI-powered policy validation frameworks using agentic and rule-based approaches.
Build scalable Python services, APIs, and automation workflows.
Develop RAG-enabled solutions and LLM-based validation agents.
Deploy, monitor, and maintain AI applications in cloud environments.
Implement CI/CD pipelines, containerized deployments, and operational tooling.
Collaborate with engineering, security, and governance teams to translate policy requirements into automated controls.
SKILLS
Must have
- Strong Python development skills, including APIs, testing, data structures, and maintainable code.
Hands-on experience with Generative AI, LLMs, prompt engineering, and RAG architectures.
Experience with AWS, Azure, or Google Cloud.
Familiarity with cloud AI services, Docker, and CI/CD practices.
Understanding of model deployment, monitoring, scalability, and Responsible AI principles.
Excellent problem-solving, communication, and collaboration skills.
Nice to have
Experience building AI/ML applications using frameworks such as scikit-learn.
Exposure to LangChain, Semantic Kernel, LlamaIndex, or similar AI orchestration frameworks.
Knowledge of governance, compliance, security controls, or policy-as-code concepts.