Job Description

Who We Are

Cross River builds the infrastructure behind the world’s most innovative financial products. Our technology and capital solutions power payments, cards, lending, and digital asset capabilities that move money safely, instantly, and inclusively — trusted by leading fintechs, enterprises, and disruptors across the globe.

Our mission is simple: to build the financial infrastructure that expands access and opportunity for all. Guided by a culture of collaboration, curiosity, and purpose, Cross River has been named one of American Banker’s Best Places to Work in Fintech year after year. Whether you’re designing code, solving regulatory puzzles, or developing strategy, you’ll join a team where innovation and integrity drive everything we do — and where your work helps shape the future of finance.

What We're Looking For

As a Senior Software Engineer, you will build the user-facing, AI-powered surface of Cross River's data platform. Our team builds the tools and applications that make the bank's data platform discoverable and genuinely useful to the people who depend on it. You'll work across our products, from a data catalog and platform-operations web app to an AI-native business intelligence interface that lets users explore, query, and reason about the data ecosystem in natural language.

This is a role for an engineer who is fluent across the entire stack (React front ends, Python APIs, relational and vector data stores, and AWS) and who is equally at home building with AI as building for it. You'll design and ship LLM-driven agents, retrieval-augmented discovery, and natural-language data experiences, wire them into well-architected and secure systems that people trust with real data, and bring AI into your own craft using modern AI-assisted development tooling. If you love turning "I wish I could just ask the data..." into a shipped feature, care deeply about correctness and data security, and want to work at the leading edge of applied AI in a regulated environment, we want to hear from you.

Responsibilities:

• Design, develop, and maintain full-stack software in support of Cross River's data platform
• Build and operate AI-native capabilities: LLM-powered agents and reasoning loops, retrieval-augmented generation (RAG) over the data catalog, and natural-language-to-SQL query experiences
• Integrate large language models responsibly, with rigorous permission checks, tracking, and observability on every model call
• Act as a thoughtful and considerate data steward, with a mind for strong data security
• Engineer React-based web UIs that present complex data (catalogs, lineage, dashboards, and conversational interfaces) clearly and accessibly
• Build and operate Python back-ends that house APIs and integrate with the data platform and adjacent systems
• Interact with AWS services and technologies including Lake Formation, Glue, Iceberg, Hive, Athena, ECS, and Snowflake
• Operate and troubleshoot and issues across the UIs, APIs, agents, and data pipelines
• Collaborate with other software engineers, data engineers, data scientists, and business personnel to ensure business, security, and operational needs are met
• Manage code and versioning effectively using Git and participate in architectural discussions on product- and platform-level designs
• Ensure best practices around development, testing, and documentation

Qualifications:

• 5+ years of experience in software engineering, with a strong focus on full-stack web and API development
• Strong front-end skills with React and TypeScript
• Strong back-end / API development skills in Python
• Hands-on experience building with large language models, such as integrating LLM APIs, agents, RAG, or other AI-powered application features
• Proven experience with AWS cloud environments (ECS, IAM, S3, and data services such as Glue, Athena, or Lake Formation)
• Strong experience with relational databases and SQL, plus Git for version control and review processes
• Very strong problem-solving skills and an enthusiasm for delivering working, performant, and operationally stable solutions

Preferred Skills:

• Experience building agentic systems, tool-use / function-calling loops, or MCP (Model Context Protocol) servers and tools
• Experience with retrieval-augmented generation and vector search (e.g. embeddings, pgvector)
• Experience building natural-language-to-SQL or other conversational data interfaces
• Experience in a regulated environment (financial services, healthcare, etc.) with an instinct for data governance
• Experience with data lake / lakehouse technologies (Iceberg, Hive, Glue) and/or Snowflake
• Fluency with AI-assisted development tools in a daily engineering workflow

#LI-JJ1 #LI-Hybrid #LI-Onsite

Salary Range: $150,000.00 - $200,000.00