Principal Engineer AI

Pennymac (NYSE: PFSI) is a specialty financial services firm with a comprehensive mortgage platform and integrated business focused on the production and servicing of U.S. mortgage loans and the management of investments related to the U.S. mortgage market.

At Pennymac, our people are the foundation of our success and at the heart of our dynamic work culture. Together, we work towards a unified goal of helping millions of Americans achieve aspirations of home ownership through the complete mortgage journey.

As the Principal Applied AI Engineer, you will be the lead architect of the "cognitive" layer of the AI platform. While the Backend Principal builds the deterministic infrastructure, you will engineer the probabilistic systems that power our "Unified Context Library" and "Agentic Orchestration" layer. You will design the autonomous workflows that turn a Product Manager’s idea into a technical specification, and a User Story into deployable code.

This role sits at the intersection of elite software engineering and applied artificial intelligence.

You will not be training foundational models from scratch; rather, you will be mastering the art of Applied AI: orchestration, retrieval-augmented generation (RAG), and the engineering of agentic systems using the AWS Bedrock Agent Core framework. You will work within the AI Platform Services division, a dedicated R&D unit tasked with delivering measurable velocity improvements to the entire organization.

• Architect the Future of SDLC:
  You will build the "Agent Factory" that drives our "conveyor belt" of software delivery, moving us from a reactive to a proactive engineering culture.
• Greenfield Innovation:
  This is a rare chance to build an enterprise-grade AI platform from the ground up, leveraging the latest in AWS Bedrock Agent Core and Agentic AI frameworks.
• High-Impact & Visibility:
  Your work will directly impact the daily lives of hundreds of engineers and product owners, reducing "Idea-to-MR" cycle times and eliminating manual
• Cutting-Edge Stack:
  Work with a modern, cloud-native stack (AWS, Node.js/Type Script) specifically tailored for high-performance AI applications.

• Design and implement sophisticated multi-agent systems that can plan, execute, and self-correct complex tasks (e.g., automated code reviews, test plan generation, and epic decomposition).
• Develop robust orchestration flows using Lang Chain.ts and AWS Bedrock Agent Core, defining how agents hand off tasks to one another and when to loop in humans for review.
• Engineer "hallucination checkpoints" and validation logic to ensure AI outputs are accurate, secure, and deterministic where necessary.
• Implement the Model Context Protocol (MCP) to standardize how our agents interface with internal tools like Jira, Git Lab, and AWS infrastructure.

• Lead the strategy for our Retrieval-Augmented Generation (RAG) foundation. You will design the pipelines that ingest, chunk, and vectorize institutional knowledge from Confluence, Jira, and Git Lab.
• Optimize Vector Database performance (e.g., Pinecone, Weaviate) and implement advanced retrieval strategies (hybrid search, re-ranking) to ensure agents possess the precise, domain-specific context needed for mortgage-tech tasks.
• Implement "memory" systems (Short-term and Long-term) that allow agents to retain context across long-running sessions and provide personalized assistance to users.

• Design and maintain the Observability & Fine-Tuning Framework, ensuring we capture every token, prompt, and user feedback signal (thumbs up/down) to systematically improve agent performance over time.
• Define and enforce Prompt Engineering best practices, creating a reusable library of system prompts that govern agent persona, tone, and output formatting.
• Build automated Evaluation Pipelines (using tools like Lang Smith or custom harnesses) to benchmark agent performance against "Golden Datasets" and prevent regression.

• Serve as the subject matter expert on Generative AI for the Platform Services division, staying ahead of the curve on LLM capabilities, cost optimization, and model selection (e.g., routing tasks between Claude 3.5 Sonnet, GPT-4o, and smaller, faster models).
• Mentor fellow engineers on the paradigm shift from deterministic coding to probabilistic AI.
• Drive the adoption of AI best practices across the wider organization.

• Elite Engineering Core:
  Bachelor’s Degree in Computer Science or equivalent, with 8+ years of professional software engineering experience. You are a software engineer first, who has mastered AI tools.
• Type Script/Node.js Expert:
  Unlike most AI roles that focus on Python, our platform is built on Node.js and Type Script. You must have deep expertise in building backend services and AI chains in this ecosystem.
• Applied AI & Agent
  
  Experience:
  
  Hands‑on experience building…