Staff Software Engineer (Customer Facing Applied AI)

Join Addepar, a leading financial technology company, as a Staff Software Engineer in the Applied AI team. In this role, you will work closely with strategic clients to identify opportunities for AI integration, prototype solutions, and partner with core engineering teams to bring those solutions to market. You will have the opportunity to shape the future of AI in finance and make a significant impact on the industry.

• Identifying client needs and building AI-powered agents and tools from prototype to production.
• Designing and implementing integrations with large language models (LLMs) and defining evaluation criteria for AI systems.
• Collaborating with core engineering teams to generalize client-specific work into product features and contributing to shared AI infrastructure.

• Comfort with SQL for data exploration and building data-grounded AI workflows
• BS/MS in Computer Science, Mathematics, or another quantitative field, or equivalent experience
• Experience with AI-assisted development tools (Claude Code, Codex, or similar)
• You see projects through from prototype to production and care about what the client experiences, not what the code does
• You've built something from zero to one. You're drawn to figuring out what to build, not just building what's specified
• Professional experience with Python (the team's primary language)
• A bias for action. You ship quickly, learn from feedback, and iterate
• Experience working with LLM APIs (Claude, GPT, or similar) including function calling and structured outputs
• 2+ years of professional software engineering experience
• Experience building agentic systems (multi-step tool use, agent orchestration, durable workflows)
• Familiarity with financial data (portfolios, transactions, securities, accounting)
• Experience with additional backend languages (Java is valuable in our environment)
• Exposure to cloud infrastructure (AWS) and container-based deployments
• Experience with evaluation frameworks or methodologies for measuring AI system quality