This is a fully remote position, open to applicants in United States.

📋 Description

• Design and develop multi-step AI agents tailored for mortgage fulfillment processes.

• Create evaluation frameworks to assess agent reliability, accuracy, and task completion.

• Enhance prompts, models, and fallbacks based on evaluation signals.

• Architect and manage agent infrastructure, including model serving, prompt pipelines, batching, queueing, and observability.

• Develop reliability features such as idempotency, retries, graceful degradation, and structured logging.

• Integrate with Encompass, DocuTech, and various third-party platforms.

• Collaborate with Encompass administrators, Fulfillment operations, and Platform engineering teams.

• Establish engineering best practices related to testing, measurement, observability, and incident response.

• Mentor engineers through code reviews and design discussions.

• Oversee workstream architecture, highlight trade-offs, and guide technical decisions.

⛳️ Requirements

• Bachelor’s degree in Computer Science, Computer Engineering, or a related technical discipline, or a comparable combination of education and experience.

• Over 8 years of professional experience in software engineering.

• Proven experience in building and managing scalable, reliable services within a modern cloud environment.

• Experience in owning an AI or ML system in production from start to finish.

• Practical experience in at least two of the following areas: designing and executing evaluation pipelines; managing LLM or ML model serving and orchestrating multi-step AI workflows; creating reliable third-party platform and external API integrations.

• Strong foundational knowledge in infrastructure and AI.

• Experience in defining correctness metrics and developing measurement tools.

• Ability to navigate ambiguity and quickly learn specialized domains.

• Mortgage industry experience is not mandatory.

• Equivalent combinations of education and experience will be considered.