Principal Engineer - AI Engineering/AI Software Engineering/Applied AI

Role Description

As a Principal Engineer on our Applied AI team, you will be at the forefront of building AI-powered software that transforms how our platform operates. You will design, build, and maintain production-grade applications and agentic systems — leveraging LLMs, agent SDKs, MCP-based tooling, and modern AI frameworks — to power critical functions from fraud investigation and decision automation to process optimization and customer communications. In this role, you will uphold high standards of reliability, evaluation rigor, and responsible AI governance across all initiatives, shipping capabilities that make a lasting impact on FICO's platform. You will collaborate with a high-caliber, multidisciplinary team and drive innovation through deep expertise in applied AI, software engineering, and systems design.

What You'll Contribute

• Design and build production AI systems — including agents, RAG pipelines, and LLM-powered workflows — that integrate seamlessly into FICO's analytics and decision management platform.
• Translate product requirements into technical designs, balancing model capabilities, latency, cost, and reliability against real-world business constraints.
• Develop robust evaluation frameworks and benchmarks to measure quality, safety, and regression across LLM-based features, and use those signals to drive iterative improvement.
• Drive end-to-end delivery of AI features, including prompt and context engineering, tool/function design, writing reusable and well-tested code, running offline and online evaluations, and communicating results to stakeholders.
• Build and operate the application layer around foundation models: orchestration, tool use, memory, retrieval, guardrails, observability, and human-in-the-loop workflows.
• Fine-tune, distill, and adapt open and closed foundation models when warranted, and align technical choices with FICO's product strategy and roadmap.
• Optimize inference performance, throughput, and cost across the serving stack — including caching, batching, routing, and model selection strategies.
• Apply modern AI engineering practices across heterogeneous infrastructure, from CPU-bound orchestration services to GPU-accelerated inference and training workloads.

Qualifications

• 12+ years Software engineering experience, with a demonstrated track record of shipping complex, production-grade systems and building applications powered by LLMs or other foundation models.
• Hands-on experience designing and deploying LLM-based features in production including prompt and context engineering, tool/function calling, agentic workflows, and evaluation-driven iteration.
• Strong coding skills in Python and/or TypeScript, with experience using modern AI SDKs and frameworks (e.g., the Anthropic, OpenAI, or Google SDKs; LangChain, LlamaIndex, LangGraph; agent frameworks; MCP).
• Solid working knowledge of how foundation models behave in practice — including their capabilities and failure modes and experience with fine-tuning, distillation, or model adaptation when product needs warrant it.
• In-depth knowledge of architectural patterns of production LLM systems, including orchestration, tool use, memory, guardrails, observability, caching, and cost/latency optimization.
• Experience with embeddings and information retrieval; hands-on experience with Retrieval-Augmented Generation (RAG) architectures and vector stores (e.g., Pinecone, Weaviate, pgvector) is strongly preferred.
• Experience building offline and online evaluation pipelines for AI systems defining metrics, building eval sets, running A/B tests, and using signals to drive iterative improvement.
• Strong problem-solving and communication skills, with the ability to mentor peers, influence technical direction, and collaborate effectively across engineering, product, and data science teams.
• Masters degree/PhD in Computer Science, a related technical field, or equivalent practical experience. Advanced degrees and open-source contributions are a plus.

Benefits

• An inclusive culture strongly reflecting our core values: Act Like an Owner, Delight Our Customers and Earn the Respect of Others.
• The opportunity to make an impact and develop professionally by leveraging your unique strengths and participating in valuable learning experiences.
• Highly competitive compensation, benefits and rewards programs that encourage you to bring your best every day and be recognized for doing so.
• An engaging, people-first work environment offering work/life balance, employee resource groups, and social events to promote interaction and camaraderie.
• The targeted base pay range for this role is: $171,500 to $269,500 with this range reflecting differences in candidate knowledge, skills and experience.