Principal Software Engineer, Applied AI - Hybrid (LLM, Agentic, Claude Code, MCP)

FactSet creates flexible, open data and software solutions for over 200,000 investment professionals worldwide, providing instant access to financial data and analytics that investors use to make crucial decisions.

At FactSet, our values are the foundation of everything we do. They express how we act and operate, serve as a compass in our decision-making, and play a big role in how we treat each other, our clients, and our communities. We believe that the best ideas can come from anyone, anywhere, at any time, and that curiosity is the key to anticipating our clients’ needs and exceeding their expectations.

We are currently seeking Principal Software Engineer to design, build, and ship AI-powered products that leverage large language models (LLMs) and agentic technologies. In this role, you will move quickly from prototype to production, turning emerging AI capabilities into reliable, high-quality solutions for FactSet’s clients. You will be a technical leader and force multiplier who sets engineering standards for applied AI, mentors other engineers, and helps shape the direction of our AI product portfolio.

You possess deep expertise in software engineering and best practices and hands-on experience building LLM-based and agentic systems , spanning orchestration, tool use, retrieval, evaluation, and observability. Proficient in AI-assisted development, you leverage tools such as Claude Code within your daily workflow and have a strong command of the modern AI-driven development lifecycle — from planning and development to review, testing, and deployment. You thrive in ambiguous, fast-paced environments where models, requirements, and tooling evolve rapidly, and you bring the technical rigor and autonomy to navigate them effectively. A collaborative and constructive voice, you set a high technical bar, drive architectural excellence, and actively contribute to the long-term direction of both product and platform.

What You'll Do

Build, test, and deploy AI-powered software

• Design and develop production-grade LLM and agentic applications, including multi-step agents, tool calling, retrieval-augmented generation, and workflow orchestration.
• Deliver stable, high-quality features adhering to best practices in testing, CI/CD, and operational readiness.
• Build and maintain evaluation frameworks, guardrails, and monitoring to optimize quality, safety, latency, and cost of AI-driven features.
• Rapidly prototype and iterate on emerging approaches, hardening successful solutions for production.
• Leverage AI coding assistants and agentic workflows to accelerate delivery while upholding quality, security, and maintainability standards.

Technical leadership, mentorship, and AI development standards

• Lead code and design reviews, providing feedback that elevates team quality, including rigorous evaluation of AI-generated code.
• Mentor engineers on applied AI patterns, agent design, and effective use of AI coding assistants, including prompting, task decomposition, and output verification.
• Define and evolve team standards for AI-assisted development, encompassing code review, testing, security, and responsible use of AI tooling across the development lifecycle.
• Stay current with advances in LLMs, agent frameworks, and developer tooling, translating insights into actionable practices for the team.

Cross-functional collaboration

• Partner with product managers, designers, architects, direct managers, and engineering peers to define the right solutions and scope.
• Plan and drive projects effectively, communicating tradeoffs, risks, and progress clearly to technical and non-technical stakeholders.

Support and continuous improvement

• Respond to bugs, incidents, and feature requests, engaging effectively across the full development and feedback lifecycle.
• Diagnose and resolve AI-specific issues, including non-deterministic behavior, hallucinations, model regressions, and prompt or tool failures.

Design, strategy, and innovation

• Lead and participate in architecture discussions and brainstorming to shape new features and platform capabilities.
• Evaluate and introduce new AI-enabled development tools and workflows that improve team productivity and product quality.
• Develop deep proficiency in FactSet’s products and data and contribute to the forward direction of our AI strategy.

What We're Looking For

Required Skills

• Bachelor’s degree in computer science or relevant.
• 8-10+ years of extensive experience developing, testing, and deploying high-quality, stable software, with a consistent record of delivering on time.
• Hands-on experience building and deploying applications using LLMs and agentic technologies (e.g., prompt engineering, RAG , function/tool calling, agent orchestration frameworks, MCP or similar protocols ).
• Hands-on familiarity with AI coding assistants such as Claude Code , and a strong grasp of how the modern AI-driven development lifecycle (AI DLC) works, including how planning, implementation, review, testing, and deployment change when AI agents participate.
• Strong software architecture and design skills, including building scalable, observable, and maintainable systems.
• Experience designing evaluation approaches for non-deterministic systems and iterating on quality using data.
• Demonstrated ability to give and receive code review feedback and to contribute forward-looking design ideas.
• Proven ability to mentor and coach other engineers on using AI coding assistants effectively, and to help establish AI development standards and guardrails for a team or organization.
• Ability to articulate FactSet’s business, client base, and how your work fits into the bigger picture.

Desired Skills

• Experience with financial data, analytics, or investment workflows.
• Familiarity with cloud platforms , containerization, and modern MLOps/LLMOps practices.
• Experience with model evaluation, fine-tuning, or optimization for latency and cost.
• Experience building cust