AI Engineer — LLM & Agent Systems

Role overview Design and ship large language model and autonomous agent systems engineered for production use, where outputs are continuously evaluated, monitored, and refined until they behave like reliable workflows rather than impressive demos. The position focuses on taking agentic AI from prototype to dependable operational tooling that other teams can depend on.

Responsibilities - Architect LLM-powered applications and agent systems that integrate with external tools, APIs, and internal data sources - Build evaluation pipelines that measure output quality, reliability, and task completion so regressions are caught before deployment - Productionize prototypes by addressing latency, cost, observability, error handling, and graceful failure modes - Collaborate with stakeholders to translate open-ended business workflows into concrete, agent-executable steps - Maintain and iterate on deployed systems based on evaluation results, user behavior, and changing requirements

Requirements - Hands-on experience building applications on top of large language models and working with agent frameworks - Strong software engineering fundamentals, including writing production-grade code, testing, and version control - Familiarity with prompt engineering techniques and an understanding of their trade-offs - Ability to design and interpret evaluation metrics for generative AI systems - Comfort working in a fast-moving area where best practices are evolving

Nice to have - Experience with retrieval-augmented generation, vector databases, or embeddings pipelines - Background in MLOps, including monitoring, logging, and cost optimization for model-backed services - Prior work deploying agents or LLM features at scale in real products