Staff AI Engineer

at SoFi · Fintech · New York, NY · Risk 2LOD

Staff AI Engineer at SoFi, focused on designing, developing, and scaling agentic AI systems for risk management and internal workflows. This role involves architecting multi-step reasoning systems, designing user experience layers, context engineering, productionizing AI services, and building observability and evaluation frameworks. Requires strong backend engineering, LLM experience, and system design skills in a financial services context.

What you'd actually do

  1. 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.
  2. 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.
  3. 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.
  4. Productionize AI Systems: Develop production-grade services and APIs, integrate agents into real systems, and ensure scalability, reliability, and maintainability.
  5. AI Observability and Evaluation: Build tracing, debugging, and evaluation frameworks to understand system behavior and continuously improve agent performance.

Skills

Required

  • 7+ years of software engineering experience
  • building and scaling AI-powered systems in production
  • working with LLMs and building applications using prompting, APIs, and/or agent frameworks
  • designing and implementing agentic systems
  • context engineering for LLM systems
  • prompt design
  • retrieval-based approaches
  • backend engineering
  • building scalable services and APIs (Python preferred)
  • cloud platforms such as AWS, Azure, or GCP
  • modern development and deployment practices
  • working with structured and unstructured data
  • building pipelines to support downstream AI applications
  • defining and implementing evaluation frameworks for AI systems
  • system design skills
  • architect scalable, reliable solutions
  • operate effectively in ambiguous problem spaces
  • translate them into well-defined systems
  • communication and collaboration skills
  • work cross-functionally
  • influence technical decisions
  • ownership mindset
  • delivering high-impact systems end-to-end

Nice to have

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

What the JD emphasized

  • agentic AI systems
  • agentic systems
  • multi-step reasoning
  • tool use
  • workflow orchestration
  • production-grade

Other signals

  • AI/ML is the role's core craft
  • ships ML models/agents/training/evals
  • design, development, and evolution of agentic AI systems
  • production-grade solutions
  • architecting, building, and scaling AI systems
Read full job description

Employee Applicant Privacy Notice

Who we are:

Shape a brighter financial future with us.

Together with our members, we’re changing the way people think about and interact with personal finance.

We’re a next-generation financial services company and national bank using innovative, mobile-first technology to help our millions of members reach their goals. The industry is going through an unprecedented transformation, and we’re at the forefront. We’re proud to come to work every day knowing that what we do has a direct impact on people’s lives, with our core values guiding us every step of the way. Join us to invest in yourself, your career, and the financial world.

The role:

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.

**What you’ll do: **

  • 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.
  • Proof of Concepts and Innovation: 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 you’ll need:

  • 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 have:

  • 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.

Compensation and Benefits

The base pay range for this role is listed below. Final base pay offer will be determined based on individual factors such as the candidate’s experience, skills, and location.

To view all of our comprehensive and competitive benefits, visit our **Benefits at SoFi **page!

SoFi provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, religion (including religious dress and grooming practices), sex (including pregnancy, childbirth and related medical conditions, breastfeeding, and conditions related to breastfeeding), gender, gender identity, gender expression, national origin, ancestry, age (40 or over), physical or medical disability, medical condition, marital status, registered domestic partner status, sexual orientation, genetic information, military and/or veteran status, or any other basis prohibited by applicable state or federal law.

The Company hires the best qualified candidate for the job, without regard to protected characteristics.

Pursuant to the San Francisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.

New York applicants: Notice of Employee Rights

SoFi is committed to an inclusive culture. As part of this commitment, SoFi offers reasonable accommodations to candidates with physical or mental disabilities. If you need accommodations to participate in the job application or interview process, please let your recruiter know or email accommodations@sofi.com.

Due to insurance coverage issues, we are unable to accommodate remote work from Hawaii or Alaska at this time.

Internal Employees

If you are a current employee, do not apply here - please navigate to our Internal Job Board in Greenhouse to apply to our open roles.