About the team
ArcaLabs builds AI agents that run sell-side workflows — public comps, IC memos, pitchbook strip profiles, earnings comp analysis — for investment banks and PE funds. We are the official FactSet AI Partner, and the team behind Arcafeed (acquired). Engineering owns the agent runtime, data pipelines, eval harness, deliverable rendering (Excel, PowerPoint, Word), and the deployment infrastructure that gets us inside customer VPCs without lighting hair on fire.
About the role
We're hiring software engineers to build the platform underneath ArcaLabs — the Claude-Agent-SDK-based runtime, the E2B sandbox layer, the FactSet integration, the workflow editor and deal-chat UI, the audit trail and eval systems, and the deliverable rendering pipeline that turns model output into pitch-ready Excel and PowerPoint. The work is half core systems, half AI engineering, half frontend, and entirely owned end-to-end.
You'll ship code that runs inside the world's largest banks, under SOC 2 Type II controls, with full audit trails on every prompt and output. We're a small team — your work will be visible the day you commit it.
What you'll do
- Build and own components of the agent runtime on the Claude Agent SDK: planning, tool use, retrieval, memory, evals, and rollouts.
- Build the persistent-agent runtime: long-lived E2B sandboxes, WebSocket bridges, checkpoint/restore, and lifecycle management for agents that span entire deal cycles.
- Extend the n8n-style workflow editor (Next.js 15, React Flow, Radix, Tailwind) and the deal-chat UI that bankers actually click on.
- Own slices of the Prisma/PostgreSQL schema as the workspace, deal, run, and sandbox models evolve.
- Wire ArcaLabs into FactSet's data APIs, customer Excel/PowerPoint/Word templates, and document stores like SharePoint, OneDrive, and Egnyte.
- Design the eval harness and review tooling that lets bankers red-team our outputs faster than humanly possible.
- Make the platform deployable in customer VPCs with single-tenant, KMS-keyed, audit-logged isolation.
- Pair with Forward Deployed Engineers to harden the patterns that show up across multiple customers into shared platform features.
You might be a fit if you
- Have 3+ years of software engineering experience with a strong track record shipping production systems.
- Are fluent in Python and TypeScript; have shipped agent-driven features in production — ideally with the Anthropic SDK or Claude Agent SDK, tool use, and sandboxed code execution.
- Are comfortable in the Excel/PowerPoint/Word object models — openpyxl, python-docx, python-pptx, ExcelJS. You've debugged a corrupt .xlsx or written formula provenance into cell comments.
- Care about the quality of the deliverable, not just the quality of the code — you'd rather ship a working comps file than a beautiful abstraction.
- Have opinions about evals, agent architecture, and data integrations, and are excited to put them into a system bankers actually use.
Bonus points
- Prior experience in fintech, capital markets, or financial data infrastructure.
- Terraform + AWS (ECS Fargate, RDS, S3, VPC). We deploy our own platform and customer single-tenant stacks via IaC.
- Webhook plumbing — Svix, AgentMail, Clerk webhooks, OAuth flows for Google / Microsoft / Egnyte.
- Experience deploying enterprise SaaS into financial institutions (SOC 2, single tenant, customer-managed keys).
Compensation
$170K – $260K + meaningful equity. Full benefits and daily breakfast, coffee, and snacks, plus complimentary fitness center access in Palo Alto.
About ArcaLabs
ArcaLabs is the official FactSet AI Partner, building AI agents that run sell-side workflows for investment banks and PE funds. We're the team behind Arcafeed (acquired) and we're hiring the founding squad in Palo Alto. We believe AI will widen, not narrow, the set of people who can do high-end finance work — and we want to ship that future.
Equal opportunity
ArcaLabs is an equal opportunity employer. We hire based on merit, and we accommodate applicants with disabilities. If you need accommodation during the hiring process, email careers@arcalabs.ai.