Role Overview

As an Applied AI Engineer at Saturn, you will be instrumental in developing, deploying, and maintaining core components of our AI platform. You will work closely with senior engineers to implement new features, ensuring they adhere to our high standards for reliability, auditability, and quality.

This role is ideal for an engineer with solid fundamentals and a deep passion for Generative AI who is eager to quickly assume full ownership of challenging, well-scoped projects within our agentic architecture.

What You'll Do

1. Component Development and Execution:

• Feature Implementation: Implement, test, and ship well-defined components of larger AI features, such as building specific RAG pipelines, defining tool functionality, or optimizing model routing.
• Engineering Fundamentals: Write clean, modular, highly-typed Python code that integrates seamlessly into our existing backend architecture, adhering to team standards for testing and maintainability.
• Contribute to Reliability: Monitor and debug production systems using tracing and observability tools, quickly escalating issues and contributing to systematic fixes under senior guidance.

2. Support Evaluation-Driven Development:

• Evaluation Execution: Execute established evaluation plans against new features and components; assist in maintaining and expanding existing Gold Standard datasets.
• Quality Adherence: Rigorously validate results against technical specifications and evaluation metrics, demonstrating a high Will to Care for output correctness and detail.
• Prompt Optimization: Practice systematic prompt engineering and experimentation, testing and documenting performance improvements on component-level tasks.

3. Rapid Domain and System Learning:

• Adopt Trust Architecture: Quickly learn and implement our Trust Architecture standards, including explicit orchestration patterns and verifiability gates.
• Gain Domain Knowledge: Actively engage with our domain experts (Guardians) and customer feedback channels to rapidly build deep context around financial advisory workflows and compliance requirements.
• Seek Feedback & Grow: Operate with high curiosity, actively seeking mentorship and feedback to quickly increase your technical scope and take on greater feature ownership.

Our 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.

What You Have

• 1-4 years of professional experience in a demanding software engineering environment.
• LLM/AI Knowledge: 2 years+ experience implementing solutions involving LLMs, RAG, and core Generative AI concepts; familiarity with systematic prompt engineering.
• Strong Software Engineering Fundamentals: Mastery of Python for high-volume backend applications, strong grasp of data structures, testing, and version control.
• System Awareness: Understanding of modern backend architecture, including APIs, services, and asynchronous processing.
• High Growth Mindset: A demonstrable desire to learn quickly, embrace new research, and operate with increasing autonomy and responsibility in a fast-paced environment.
• Attention to Detail: A focus on quality and precision, essential for building reliable systems in a regulated domain.
• Product & User Focus: Strong product sense and the drive to quickly build domain expertise, translating user needs and compliance context into high-value technical solutions