Staff Software Engineer - AI Integrations

We believe that the way people interact with their finances will drastically improve in the next few years. We’re dedicated to empowering this transformation by building the tools and experiences that thousands of developers use to create their own products. Plaid powers the tools millions of people rely on to live a healthier financial life. We work with thousands of companies like Venmo, SoFi, several of the Fortune 500, and many of the largest banks to make it easy for people to connect their financial accounts to the apps and services they want to use. Plaid’s network covers 12,000 financial institutions across the US, Canada, UK and Europe. Founded in 2013, the company is headquartered in San Francisco with offices in New York, Washington D.C., London and Amsterdam.

Team

The Instant Access (AI Integrations) team, part of the Network Enablement and Access (NEA) organization, builds applied AI systems based on LLM’s that operate autonomously in production. This foundational AI work is directly tied to NEA's most important priorities. Our current focus is automatically creating, repairing, and improving the thousands of long-tail integrations that enable millions of Plaid consumers to connect to their financial institutions. Our goal is for every long-tail institution to be supported by Plaid, with any issues detected, triaged, and resolved automatically.

Role

As a Staff Software Engineer on Instant Access, you'll set technical foundations for autonomous systems that operate directly in production. You'll work across AI and product engineering to solve ambiguous, high-impact problems, while designing systems that can reason about failures, generate solutions, and safely take action at scale.

This is a hands-on role that combines deep technical leadership with implementation. You'll partner closely with engineers, product managers, and leaders across NEA to identify opportunities for automation, define long-term architecture, and build the foundational systems that future AI initiatives will rely on.

As an early engineer on the team, you'll significantly influence technical direction and the evolution of a new capability. This could fundamentally change how Plaid builds and operates software.

Responsibilities

• Define the technical direction and architecture for autonomous AI systems that create, repair, and improve financial institution integrations.
• Create novel observability, monitoring, and debugging platforms to provide engineers with deep visibility into the behavior, decisions, and performance of AI-powered systems.
• Build LLM-powered code generation pipelines that write, validate, and ship production code end-to-end with minimal human intervention.
• Design evaluation frameworks that measure correctness, reliability, and safety for non-deterministic systems operating at scale.
• Architect self-healing infrastructure that detects, diagnoses, and repairs itself in under 24 hours.
• Develop multi-layer safety architectures to ensure AI systems take the correct actions in production and degrade safely when uncertainty exists.
• Partner closely with engineering and product leaders to identify high-leverage automation opportunities and turn them into production systems.
• Raise the technical bar across the organization through mentorship, design reviews, and hands-on leadership.

Qualifications

Must Haves:

• 8+ years of strong software engineering experience with a deep focus on backend and/or platform systems
• Ability to balance divergent thinking (exploring possibilities) with convergent thinking (evaluating feasibility)
• Must be comfortable working hands-on directly in the codebase. This is a builder archetype position. You will spend considerable time designing and then building the actual systems you own.
• Must be comfortable moving fast, which means making trade-offs between technical excellence and the rapid deployment of working systems to validate whether approaches are fruitful.

Nice to Haves:

• Previous experience building production generative AI systems that customers interact with
• Experience with browser automation, web automation, scraping, extraction systems, or tools such as Playwright, Stagehand, or similar frameworks

Our mission at Plaid is to unlock financial freedom for everyone. To support that mission, we seek to build a diverse team of driven individuals who care deeply about making the financial ecosystem more equitable. We recognize that strong qualifications can come from both prior work experiences and lived experiences. We encourage you to apply to a role even if your experience doesn't fully match the job description. We are always looking for team members that will bring something unique to Plaid!

Plaid is proud to be an equal opportunity employer and values diversity at our company. We do not discriminate based on race, color, national origin, ethnicity, religion or religious belief, sex (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender, gender identity, gender expression, transgender status, sexual stereotypes, age, military or veteran status, disability, or other applicable legally protected characteristics. We also consider qualified applicants with criminal histories, consistent with applicable federal, state, and local laws. Plaid is committed to providing reasonable accommodations for candidates with disabilities in our recruiting process. If you need any assistance with your application or interviews due to a disability, please let us know at accommodations@plaid.com.

Please review our Candidate Privacy Notice here.

Additional compensation in the form(s) of equity and/or commission are dependent on the position offered. Plaid provides a comprehensive benefit plan, including medical, dental, vision, and 401(k). Pay is based on factors such as (but not limited to) scope and responsibilities of the position, candidate's work experience and skillset, and location. Pay and benefits are subject to change at any time, consistent with the terms of any applicable compensation or benefit plans.