Why Saturn?

Saturn is revolutionizing financial services with AI, building the operating system for financial advisors. Our mission is to democratize financial advice for one billion people by providing the world's most trusted, intelligent platform for financial planning and compliance.

This is a rare chance to build a category-defining company in a high-stakes, regulated environment. We operate with a Dual Mandate: relentless Speed of Execution to deliver reliable, robust products today, and dedicated Speed of Learning to explore the frontier of AI and unlock the next generation of features.

If you are driven by the pursuit of greatness, thrive on end-to-end ownership, and want to build the gold standard for AI trust and reliability, we invite you to build with us.

Role Overview

As a Staff Applied AI Engineer, you are the core architectural leader responsible for scaling Saturn’s AI platform, transforming it into a high-reliability operational system that can support complex, interconnected workflows.

This role moves beyond ownership of a single feature. You will define the strategic, long-term technical direction for our core systems—the orchestration, evaluation, and data governance layers—that enable dozens of different AI capabilities to be built concurrently and reliably composed into advisory workflows. You will tackle the hardest, most ambiguous technical challenges, acting as a technical force multiplier across the entire engineering organization, driven by a deep care for the systems' robustness and the customer's experience.

What You'll Do

1. Define and Scale the Agentic Platform Architecture:

• Strategic System Ownership: Own the architecture and scaling roadmap (12-18 months) for our core AI infrastructure, ensuring it supports rapid development while maintaining quality, performance, and compliance standards necessary for enterprise adoption.
• Workflow Composition: Architect and govern systems for dynamic, context-aware capability composition, component isolation, and prompt versioning. Ensure the platform can reliably support multi-step, long-running agentic workflows that multiple engineering teams can extend simultaneously without conflicts.
• Reliability Backbone: Design and implement fault-tolerant infrastructure, including high-volume backend components, model-agnostic routing, advanced fallbacks, and performance optimization for mission-critical paths.

2. Drive Organizational Quality and Trust Standards:

• Evaluation Framework Ownership: Own the architecture of the comprehensive evaluation framework, ensuring the infrastructure supports both systematic offline testing and continuous online evaluation (A/B testing, canary rollouts) and that evaluations serve as non-negotiable CI/CD gates.
• Trust Specification & Governance: Define and enforce the technical specification for trust architecture and data governance, ensuring every generative output maintains a verifiable, auditable record, crucial for regulated environments.

3. Provide Technical Leverage and Leadership:

• Unblock Ambiguity: Take on highly unstructured, cross-team technical problems, defining the path forward through deep analysis and rapid prototyping.
• Mentorship and Influence: Act as a technical mentor and leader for Senior and other Staff Engineers, raising the bar for architectural quality, code maintainability, and defensive engineering practices.
• Decisive Action: Lead significant architectural reviews and decisions, driving consensus on complex trade-offs (latency vs. cost vs. quality) with clarity and speed.

What You Have

• 8+ years of progressive experience in ML/software engineering, with at least 3 years focused on architecting, deploying, and operating scaled production systems powered by AI or Machine Learning.
• B2B SaaS and Workflow Expertise: Proven track record of architecting and scaling backend platforms in a fast-growing B2B software environment. Direct experience designing systems that handle complex, multi-user workflow orchestration, state management, and long-running tasks (e.g., engines for compliance, legal, finance, or heavy operational automation) is highly preferred.
• Deep Systems Thinking: Expertise in distributed systems, high-volume backend architecture (Python mastery required), and designing systems for auditability and compliance in regulated environments. You should be able to reason about the entire software stack, not just the ML components.
• Platform-Level Scaling Experience: Experience in managing the complexity inherent in interconnected, large-scale agentic systems, including model composition, prompt governance, and component isolation for multi-team contribution.
• Evaluation & Quality Discipline: Extensive experience designing, implementing, and enforcing evaluation strategies at an organizational level, turning real-world failures into systematic regression tests.
• Architectural Leadership: A history of successfully leading and delivering complex, multi-quarter technical roadmaps; highly effective at communicating complex technical concepts to both engineering peers and business stakeholders.
• Bias for Simplicity: A clear philosophy of choosing straightforward, maintainable solutions over clever but fragile complexity, especially when dealing with probabilistic systems.

Saturn Values in Practice:

• Earn Trust: Building verifiably correct, explainable systems (Citation-First, Adviser-in-the-Loop).
• Pursue Greatness: Driving our Evaluation-Driven Development flywheel to compound quality daily.
• Seek Truth: Relying on data, traces, and customer feedback (Guardians) to inform every decision.
• Be Audacious: Taking decisive ownership and building intelligent agents that solve previously unsolvable problems in finance.
• Will to Care: Obsessively anticipating customer needs and building systems with extreme attention to detail, ensuring long-term quality, reliability, and the success of our users and peers.