Forward Deployed Engineer, Frontier Engineering

Role overview

Build and deploy AI applications for complex enterprise use cases, partnering directly with customer engineering and data science teams. The role spans the full delivery cycle—from early prototypes to secure production systems—with a strong focus on measuring and improving the quality, reliability, and safety of LLM and agent workflows.

Responsibilities - Turn customer goals into production-ready AI applications, including retrieval-augmented and agent-based systems. - Build solutions and data pipelines with Python and SQL, and own deployment, monitoring, and ongoing optimization. - Define quality measures, evaluation datasets, and repeatable test cycles; use results to improve accuracy and catch regressions. - Add safeguards, observability, and human review processes, and use production feedback to refine evaluations. - Advise customer technical teams and share field learnings with internal product and engineering groups. - Work onsite with customers for at least 25% of the time and travel as needed.

Requirements - A bachelor’s degree in computer science, engineering, or a related field, or equivalent practical experience. - At least three years of professional software engineering experience. - Experience building LLM applications, especially with retrieval-augmented generation or agent workflows. - Practical experience defining quality measures and evaluating LLM or agent systems to improve results. - Strong problem-solving and communication skills, including the ability to explain technical topics to varied audiences. - Willingness to travel and comfort working through ambiguity in a fast-changing field.

Nice to have - Experience creating evaluation sets from production traces or synthetic data, and comparing approaches through structured experiments. - Familiarity with evaluation and observability tools or custom evaluation harnesses, and with analyzing failure modes in retrieval or agent systems. - Cloud MLOps experience, including deployment, monitoring, and evaluation; familiarity with data science libraries and tools. - Experience in a customer-facing technical role or an early-stage company.