Overview
The AI Engineer - LLM & Agentic Systems role is designed for seasoned professionals who have experience in creating and deploying large language model (LLM)-powered systems within production environments. Working in a hybrid setting, the engineer will collaborate closely with various engineering teams to design and build complex AI agents and workflows, ensuring the integration of AI into core business processes. This position emphasizes hands-on experience and the ability to take projects from initial exploration through to production and iteration at scale.
Responsibilities
- Design and build AI agents and workflows using LLMs, RAG, reasoning, memory, and tool orchestration.
- Own the delivery process end-to-end, from exploration to production deployment and ongoing iteration.
- Integrate AI into products, APIs, and core business workflows with a focus on usability and performance.
- Collaborate with engineering teams to ensure systems are observable and maintainable.
- Utilize MCP-style architectures and frameworks to construct scalable systems.
Requirements
- Proven experience in deploying LLM-powered systems in production environments.
- Hands-on experience in building AI agents with multi-step reasoning and tool orchestration.
- Strong Python skills and a solid understanding of machine learning principles.
- Experience with cloud deployment on AWS, GCP, or Azure using modern engineering practices.
- A Master's degree or higher in a relevant field such as mathematics, science, or computer science.
- A product mindset focused on impact and adoption of AI solutions.
- Background in SaaS, B2B AI products, or large-scale AI transformations is preferred.