<h2><strong>About Goodfin</strong></h2>
<p>Goodfin is an AI-native wealth platform focused on private markets. We’re building intelligent, agentic systems that help accredited investors research, evaluate, and act on private investment opportunities with clarity and confidence.</p>
<p>This is not an AI “feature.” <strong>AI <em>is</em> the product.</strong></p>
<p>As a Staff AI Engineer, you’ll be a technical leader responsible for designing, building, and hardening the core intelligence systems behind Goodfin—systems used by real investors making real financial decisions.</p>
<p>This is a hands-on role for someone who wants to work at the boundary of what’s reliable in applied AI—and make it production-grade. You’ll own end-to-end systems: from architecture and modeling decisions through deployment, evaluation, and iteration. You’ll also help define technical standards and shape how we build AI as a company.</p>
<hr>
<h2><strong>What You’ll Work On</strong></h2>
<ul>
<li>Architecting LLM-powered, agentic systems for private market research, analysis, and decision support</li>
<li>Designing hybrid reasoning pipelines that combine LLMs with retrieval, structured financial data, rules, and tools</li>
<li>Building robust RAG pipelines over unstructured, noisy, and proprietary data (PPMs, decks, filings, internal memos)</li>
<li>Developing evaluation frameworks for reasoning quality, faithfulness, latency, and cost</li>
<li>Implementing observability, debugging, and failure-handling for multi-step AI workflows</li>
<li>Partnering closely with business and design to translate ambiguous user needs into reliable intelligent behavior</li>
<li>Raising the bar on AI engineering practices across the team through example and mentorship</li>
</ul>
<p>**Concrete Example<br>
**Build an AI deep research analyst that can synthesize deal documents, market data, news articles, and comparable deals into actionable, well-sourced insights—while surfacing nuances rather than hiding it.</p>
<hr>
<h2><strong>Why This Is Hard</strong></h2>
<ul>
<li>
<strong>Product intuition matters:</strong> We’re building a sticky, high-value product for real investors—not a demo or internal research tool.</li>
<li>
<strong>High-stakes domain:</strong> Private market investing requires accuracy, explainability, and calibrated uncertainty. “Mostly right” is not acceptable.</li>
<li>
<strong>Data complexity:</strong> There is no clean source of truth. Data is fragmented, sparse, and often contradictory.</li>
<li>
<strong>Reasoning over generation:</strong> The challenge is building systems that reason, compare tradeoffs, and surface uncertainty—not just generate fluent text.</li>
<li>
<strong>Agent reliability:</strong> Multi-step, tool-using agents must behave consistently in production, not just in demos.</li>
<li>
<strong>Evaluation is unsolved:</strong> You’ll help define what “good” looks like when traditional ML metrics fall short.</li>
<li>
<strong>Trust as a system property:</strong> Explainability, sourcing, and failure modes are core technical requirements—not UX afterthoughts.</li>
</ul>
<hr>
<h2><strong>What We’re Looking For</strong></h2>
<ul>
<li>6+ years of software engineering experience, with deep hands-on work in applied AI / ML systems</li>
<li>Strong fundamentals in Python and backend system design</li>
<li>Proven experience with LLMs (prompting, fine-tuning, RAG, agentic workflows, or evaluation tooling)</li>
<li>Experience owning ambiguous, high-impact systems from concept to production</li>
<li>Comfort making architectural tradeoffs under real-world constraints</li>
<li>Ability to think at the system level while still shipping high-quality code</li>
<li>High product intuition and a strong sense of responsibility for user outcomes</li>
</ul>
<p><strong>Bonus</strong></p>
<ul>
<li>Experience in fintech, data-intensive products, or regulated environments</li>
</ul>
<hr>
<h2><strong>How We Work</strong></h2>
<ul>
<li>Small, lean team with high ownership and minimal bureaucracy</li>
<li>Direct access to users and fast feedback loops</li>
<li>Str