Aleph · posted · checked
Staff+ Software Engineer, AI
$130k – $350kRemote · Americas and Latin AmericaStaff+
Who can apply
Remote · Americas and Latin America
Location: Americas
ABOUT ALEPH
Aleph is an AI-native platform for Financial Planning & Analysis (FP&A), an established software category with a multi-billion market but no clear winner. We’re trying to solve a problem many finance teams are super familiar with: data scattered across a million systems, endless spreadsheets and way too much time spent getting numbers to line up instead of actually using them to make decisions.
Aleph was founded by Albert Gozzi and Santiago Perez De Rosso, two technical founders with backgrounds from Stanford and MIT and experience working at top-tier companies such as Google, Microsoft and Bain & Company. We’re backed by top VCs (Khosla Ventures, Bain Capital Ventures, YC, Picus Capital), and work with customers like Webflow, Notion, Zapier, Y Combinator and many others.
We are hiring remotely across the Americas (United States, Canada, LATAM).
THE CHARTER
Every AI feature at Aleph - asking questions of your financials, agents that do full FP&A workflows - runs on a shared foundation: which model handles which task, what context the model sees, what tools it can call, and how we measure whether it's getting better. Today those decisions live inside product teams. This role owns them as a whole, including the model proxy and eval infrastructure everything runs through.
WHAT YOU'LL DO
Own the AI foundation product teams build on: model selection and routing, the model proxy layer, context management, and tool design
Own eval infrastructure. Work with customers and finance domain experts to define what excellent output looks like, then encode it in evals every team can run - in FP&A, a wrong answer ends up in someone's board deck
Ship agentic features end to end, from v0 through the optimization loop: prompt and context engineering, caching, parallel tool calls, subagent patterns
Build observability into agent behavior so we can profile it, find bottlenecks, and decide what to fix with data
Track what's changing in agentic systems and bring the practices that prove out into how we build
WHAT WE'RE LOOKING FOR
You've shipped production LLM systems - evals, context management, multi-model or multi-provider routing - and can talk concretely about what broke and what you changed