Staff AI Engineer

SoFi • San Francisco, CA

20h

About The Position

SoFi’s Staff AI Engineer is a highly experienced, hands-on individual contributor within SoFi’s growing independent risk organization, focused on owning the design, development, and evolution of agentic AI systems to solve real-world, high-impact problems. This role will be instrumental in architecting, building, and scaling AI systems that enhance risk management and internal workflows, with a focus on creating reliable, reusable, and production-grade solutions. This role operates at the intersection of the intelligence layer, including LLMs, agents, and orchestration, and the experience layer, which defines how users interact with and derive value from AI systems. You will shape how these systems are designed and integrated into critical workflows, ensuring they are intuitive, reliable, and effective in high-stakes risk environments. You will work closely with the Senior Manager of AI Engineering as well as business stakeholders, to translate complex, ambiguous problems into scalable, production-grade AI systems with measurable impact.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Data Science, Artificial Intelligence, Machine Learning, or a related field.
• 7+ years of software engineering experience, with significant experience building and scaling AI-powered systems in production.
• Strong experience working with LLMs and building applications using prompting, APIs, and/or agent frameworks.
• Experience designing and implementing agentic systems, including patterns such as tool use, multi-step reasoning, and workflow orchestration.
• Deep experience in context engineering for LLM systems, including structuring inputs and outputs, prompt design, and retrieval-based approaches.
• Strong backend engineering experience, including building scalable services and APIs (Python preferred).
• Experience designing systems on cloud platforms such as AWS, Azure, or GCP, with an understanding of modern development and deployment practices.
• Experience working with structured and unstructured data, including building pipelines to support downstream AI applications.
• Experience defining and implementing evaluation frameworks for AI systems, including metrics, experimentation, and performance iteration.
• Strong system design skills, with the ability to architect scalable, reliable solutions.
• Ability to operate effectively in ambiguous problem spaces and translate them into well-defined systems.
• Strong communication and collaboration skills, with the ability to work cross-functionally and influence technical decisions.
• Demonstrated ownership mindset, with a track record of delivering high-impact systems end-to-end.

Nice To Haves

• Experience designing and building user-facing workflows or internal tools powered by AI.
• Familiarity with observability and evaluation tools for AI systems such as Langfuse, LangSmith, or similar.
• Experience working in financial services or building systems for risk-related use cases.
• Experience with frontend technologies such as React for building AI-powered interfaces.
• Experience contributing to shared platforms, libraries, or internal tooling that enable reuse across teams.
• Experience building systems that require explainability, auditability, or operate in regulated environments.

Responsibilities

• Architect and Develop Agentic AI Systems: Lead the design and development of AI systems that leverage multi-step reasoning, tool use, and structured workflows, using frameworks such as LangGraph or similar approaches. Incorporate planning, memory, tool integration, and adaptive control flow to enable automated decisioning, risk insights, and internal platforms.
• Design the Experience Layer: Define how users interact with AI systems by designing workflows, interfaces, and feedback loops that drive adoption, usability, and trust. This will involve close coordination with users / stakeholders. Ensure alignment between system behavior and user expectations.
• Context Engineering and System Design: Define and implement approaches for structuring inputs, outputs, and system context to improve reliability and performance of LLM systems, including prompt design, retrieval strategies, and workflow composition.
• Productionize AI Systems: Develop production-grade services and APIs, integrate agents into real systems, and ensure scalability, reliability, and maintainability.
• AI Observability and Evaluation: Build tracing, debugging, and evaluation frameworks to understand system behavior and continuously improve agent performance.
• Cross-Functional Collaboration: Partner with risk, engineering, and business teams to translate ambiguous problems into working AI systems and deliver measurable outcomes.
• Innovation and Prototyping: Identify high-impact opportunities to apply AI, rapidly prototype solutions, and evaluate emerging tools and approaches to inform long-term system design aligned with latest trends in AI.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior