Automation Engineering, Tech Lead

Position Overview: We are seeking a highly experienced Senior Software Developer / Technical Lead in Automation Engineering and AI Solutions Development to design, build, and maintain scalable Python applications that power our in-house agentic GenAI solutions. This is primarily a hands-on software engineering role. You will own the end-to-end development of robust backend services, APIs, and automation frameworks, applying strong software engineering fundamentals to AI-enabled systems. You will lead the development of production-grade GenAI solutions leveraging technologies such as LLMs, RAG architectures, and vector databases within modern cloud-native frameworks while ensuring scalability, reliability, and responsible AI practices. Our Impact At Freddie Mac, our mission of Making Home Possible drives everything we do. As we advance into an AI-powered future, we are transforming how risk management is designed, implemented, and scaled - moving from manual processes to intelligent, automated, and embedded risk capabilities. This role is part of a next-generation initiative to reimagine risk management through GenAI and automation, where controls are engineered into systems, not just documented.

Your Impact: In this role, you will lead the design, build, and maintenance of Python-based microservices, APIs, and backend services that power scalable GenAI applications, AI agents, and agentic workflows. You will lead automation framework design, build and optimize RAG pipelines and vector search solutions, and ensure efficient deployment, high system performance, and well-tested, maintainable code. Design, build, and operate MCP (Model Context Protocol) servers that serve as the backbone of our agentic AI solutions encapsulating internal logic including Panel of Experts orchestration, Judge-Draft-Refine loops, RAG retrieval, and tool-calling integrations. Design and implement multi-agent systems, including Lead Agent and Reviewer Agent patterns, consensus mechanisms, and iterative refinement loops that ensure quality, accuracy, and auditability of AI-generated outputs. Create data pipelines and feature engineering workflows, establish feedback loops for continuous improvement, and integrate AI capabilities into production systems. As part of building these systems responsibly, you will help embed risk and control mechanisms into GenAI workflows and partner with Risk, Security, and Governance teams to translate requirements into reliable code. Build observable and auditable AI systems with structured metadata, run-level logging, traceability, and audit trails ensuring outputs are explainable and traceable in a regulated environment. Establish Python project standards, scaffolding templates, and development best practices that accelerate team onboarding and reduce setup friction. Collaborate across engineering, product, risk, security, and governance teams; provide technical leadership grounded in engineering excellence; and communicate complex issues, decisions, and recommendations clearly to both technical and executive audiences. Proactively identify and raise technical, delivery, risk, and dependency concerns; lead escalations through resolution; and communicate issues, tradeoffs, and recommended actions clearly and concisely to leadership.

Qualifications: Bachelor's degree in computer science, Engineering, or a related field (advanced degree preferred) 8-10+ years of experience in software engineering Strong proficiency in Python, including experience building production-grade APIs, microservices, automation frameworks, and backend services Experience building AI-enabled applications, automation platforms, or intelligent software solutions Experience integrating LLMs and AI services into business applications, including familiarity with RAG, prompt engineering, or similar AI patterns Experience with MLOps/DataOps pipelines, observability, and monitoring tools Familiarity with vector databases and modern AI architectures Experience with platforms such as AWS Bedrock, Azure OpenAI, and GitHub Copilot Experience with LLM evaluation, guardrails, or AI safety mechanisms Familiarity with AI governance, model risk, or responsible AI frameworks Experience implementing risk, control, or compliance requirements in technical systems Experience building or working with MCP (Model Context Protocol) servers or equivalent tool-calling and agent-serving frameworks Experience designing or building multi-agent systems, including agent orchestration, Lead Agent / Reviewer Agent patterns, review loops, and consensus mechanisms Experience with agentic frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or similar Experience buildin