SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Addepar is a global data and AI platform that helps investment professionals turn complex financial information into actionable intelligence. The company unifies portfolio, market, and client data to deliver AI-powered insights within investment and client workflows. More than 1,500 firms in 60 countries use Addepar to manage and advise on nearly $10 trillion in assets.
The Applied AI team works embedded with Addepar's strategic clients to identify where AI can transform their workflows and then build those capabilities from scratch. In this role, you will build agentic systems end-to-end—from understanding the client's problem, prototyping quickly, proving it works, and partnering with core engineering teams to ship it as a product for all customers.
You'll spend time understanding a client's world and workflows, identify what's worth building, design agent behavior, wire up tool integrations, and tune evaluations until the AI actually works in practice. You'll sit close to the people who use what you build, and that feedback loop drives both product and skill growth. The team is new, and your work shapes what gets shipped.
Key responsibilities include:
- Build AI-powered agents and tools end-to-end: identify problems with clients and domain experts, prototype quickly, evaluate rigorously, and ship to production
- Design and implement LLM integrations including prompt engineering, function calling, structured outputs, and retrieval-augmented workflows
- Define evaluation criteria and build test harnesses for AI systems where correctness is ambiguous and domain-specific
- Work directly with clients to understand their workflows, validate AI behavior, and iterate toward production quality
- Partner with core engineering teams to generalize client-specific work into product features
- Contribute to shared AI infrastructure (agent frameworks, tool integrations, deployment pipelines)
- Monitor and maintain production AI systems with attention to reliability, cost, and performance
This role may require occasional work outside standard business hours to accommodate client time zones and up to 15% travel to client sites, including occasional overnight and multi-day engagements.
Requirements:
- Extensive professional software engineering experience
- Professional experience with Python (the team's primary language)
- Experience working with LLM APIs (Claude, GPT, or similar) including function calling and structured outputs
- Comfort with SQL for data exploration and building data-grounded AI workflows
- Experience with AI-assisted development tools (Claude Code, Codex, or similar)
- Demonstrated ability to build something from zero to one; drawn to figuring out what to build, not just building what's specified
- Bias for action: ship quickly, learn from feedback, and iterate
- See projects through from prototype to production and care about what the client experiences
- BS/MS in Computer Science, Mathematics, or another quantitative field, or equivalent experience
- Must have and maintain the right to work in the United Kingdom from the first day of employment; visa sponsorship is not available
Nice to have:
- Experience building agentic systems (multi-step tool use, agent orchestration, durable workflows)
- Experience with additional backend languages (Java is valuable in the environment)
- Familiarity with financial data (portfolios, transactions, securities, accounting)
- Exposure to cloud infrastructure (AWS) and container-based deployments
- Experience with evaluation frameworks or methodologies for measuring AI system quality
