Staff Software Engineer - AI Applications
$265k - $370k • Remote • San Francisco HQ • FullTime
Posted 1mo ago
Job Location
San Francisco HQ
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Agent Engineer
About the job
Plaid is at the forefront of transforming the financial industry through AI. As a founding member of the newly formed AI Applications Team, you will play a pivotal role in scaling successful AI initiatives and accelerating Plaid's evolution into an AI-first company. This role offers the unique opportunity to lead projects that enable and scale our business with major AI customers and partners, starting with personal finance use cases and expanding into diverse areas. You will be instrumental in defining the future of AI in FinTech, from how consumers manage their finances to how developers build applications.
Responsibilities
- Develop and evolve preferred integration patterns for Plaid with AI providers, including API adaptations and building official Plaid MCP Servers.
- Redefine how Plaid's consumer link experience is embedded into conversational interfaces seamlessly.
- Architect the trust layer for agentic commerce to become an industry standard.
- Scale and extend homegrown AI-powered customer support agents, including implementing multi-turn and multi-agent systems.
- Define scalable offline evaluation methods for complex multi-turn open-ended tasks.
- Research and prototype the use of Human-In-The-Loop - Reinforcement Learning (RLHF) for an insights flywheel.
- Pioneer architectures for customer-specific long-term memory.
- Extend agentic systems to support critical customer journey areas like product recommendation, onboarding, risk diligence, and upselling.
- Design, develop, and maintain scalable backend services and APIs.
- Design and implement intuitive, high-quality frontend applications.
- Collaborate with AI engineers, software engineers, and machine learning engineers to architect and implement GenAI-powered products.
- Collaborate across functions to understand user needs and propose/implement high-impact AI solutions.
- Design and execute rapid experiments to explore business impact from emerging AI capabilities using minimal viable testing approaches.
- Balance creative exploration with rigorous evaluation of technical feasibility, product potential, and business impact.
Requirements
- Experience building backend services and working with microservices or service-oriented architectures.
- Hands-on experience working with LLMs to build and ship products.
- Experience with prompt engineering.
- Experience with fine-tuning LLMs.
- Experience with retrieval augmented generation (RAG).
- Experience with semantic search, including vector databases and embedding models.