Principal Software Engineer

Let's begin Principal Software Engineer (15583)

At Moody's, we unite the brightest minds to turn today's risks into tomorrow's opportunities. We do this by striving to create an inclusive environment where everyone feels welcome to be who they are—with the freedom to exchange ideas, think innovatively, and listen to each other and customers in meaningful ways. Moody's is transforming how the world sees risk. As a global leader in ratings and integrated risk assessment, we're advancing AI to move from insight to action—enabling intelligence that not only understands complexity but responds to it. We decode risk to unlock opportunity, helping our clients navigate uncertainty with clarity, speed, and confidence.

Skills and Competencies

• 10+ years of software engineering experience, including delivering complex, multi-team initiatives with
  measurable business impact, and experience setting technical direction as a principal, staff or lead engineer, with
  a strong track record of remaining hands-on in software design, development and delivery while providing
  technical leadership.
• Strong hands-on experience building enterprise AI applications on large language models, including agents,
  orchestration frameworks, retrieval-augmented generation (RAG), tool use, and evaluation frameworks.
• Experience designing multi-agent or subagent architectures and successfully taking agentic systems from
  prototype to production deployment.
• Knowledge or practical experience with the Model Context Protocol (MCP), tool-based architectures, tool
  registries, and governance controls including guardrails, permissioning, auditing, and human approval workflows.
• Hands-on experience with modern AI frameworks such as LangChain, LangGraph, Langfuse, or equivalent
  technologies.
• Strong proficiency in Python and experience with cloud-native technologies including Docker, Kubernetes, API
  gateways, event-driven architectures, and relational or vector data stores.
• Experience running AI systems in production environments, including observability, cost management, regression
  detection, robustness testing, and incident response.
• Demonstrated ability to influence technical direction across teams, communicate complex architecture to
  technical and non-technical audiences, and drive adoption of new engineering tools and practices.
• Deep expertise in artificial intelligence, with a track record of implementing advanced AI solutions to drive
  strategic transformation and operational efficiency. Strong experience using AI tools to lead innovation initiatives.
• Demonstrated leadership in managing AI-related risks, ensuring ethical governance, and fostering a culture of
  responsible AI adoption across the organization.

Education

• Bachelor's or master's degree in Computer Science, Engineering, Artificial Intelligence, or a related discipline, or
  equivalent professional experience.

Responsibilities

• Lead the strategy, architecture, development, and delivery of secure, scalable agentic AI capabilities that power
  the Insurance Life platform.
• Co-define and drive the technical architecture and roadmap for the AXIS Cloud AI orchestration layer, including
  dynamic tool selection, subagent orchestration patterns, decision APIs, and a governed MCP-based tool registry,
  in close collaboration with the broader architecture team.
• Actively contribute to the design, implementation, and delivery of the AI orchestration platform, working hands-on
  alongside the engineering team while providing technical leadership and guidance.
• Drive key technical decisions and translate architectural direction into pragmatic engineering solutions and
  implementation guidance for the team.
• Lead innovation in agentic AI by prototyping emerging technologies and patterns, including agent harnesses,
  generative user interfaces, skills, and long-running workflows, and advancing successful concepts into
  production-ready solutions.
• Prioritize pragmatic, end-to-end vertical solutions that demonstrate customer value while progressively building
  the broader orchestration platform.
• Design secure and transparent AI systems through security middleware, audit capabilities, logging, metrics,
  human approval checkpoints, and recovery mechanisms including retry and resume capabilities.
• Refactor and modernize existing large language model applications and frameworks onto a shared orchestration
  layer while partnering with platform, authentication, and integration teams.
• Deploy, operate, and optimize AI services in Kubernetes environments, establishing observability, evaluation
  frameworks, guardrail testing, and cost and capacity management practices.
• Collaborate close