C
Senior AI Engineer — Agentic Workflows
Chiara Lombardi
Full-time · Senior · Los_Angeles
About the role
We spent three years building a no-code workflow automation tool. It didn't work. Not because the technology was wrong, but because we could never find a repeatable go-to-market motion — the tool was genuinely useful to too many different types of people in too many different ways to build a focused sales process around it. We shut the product down in October, gave our investors a choice between a wind-down or a pivot, and made the case for the pivot. They backed us. What we are building now is narrower and more specific: an AI agent layer for accounting firms, automating the document review, categorisation, and query workflows that currently consume 60–80% of junior accountant time in most practices. We have spent four months talking to 31 accounting firms. We have two paying pilot customers and a clear picture of the problem. We have nine months of runway. We need to ship a product that justifies a Series A in that window. We are telling you all of this because we think you deserve the full picture before you apply to join us. The risk is real. The opportunity is real. The team has been through a hard experience and come out of it with significantly better judgement about what it takes to build a company. If you want to join a team that has already made the expensive mistakes and is now using that knowledge carefully, this might be an interesting place.
Responsibilities
- Design and implement the AI agent workflows that automate document review, categorisation, and query handling for accounting firm workflows
- Build the document processing and retrieval pipeline for financial documents: tax filings, invoices, ledger exports, and client correspondence
- Own evaluation — define what good looks like for each workflow and build automated tests that catch regressions
- Work directly with pilot customers to understand where the agents fail and translate that into engineering priorities
- Contribute to architectural decisions with a co-founder team that values engineering judgement
Requirements
- 5+ years of software or ML engineering with at least 2 years building LLM-powered applications that reached real users
- Python — production-grade code you're comfortable shipping into a paying customer's workflow
- LangChain for agentic workflow design — multi-step reasoning chains, tool use, and memory management in production
- OpenAI API at depth: structured outputs, function calling, context management, and cost optimisation under real usage
- RAG pipeline experience — document ingestion, chunking, retrieval, re-ranking, and evaluation
- Docker for containerised deployment in customer-controlled environments — some accounting firms have strict data residency requirements
- Experience building software for regulated professional services is a genuine advantage
Benefits
- Genuine early-stage equity in a company with a clear problem, paying customers, and a team that has learned from a previous attempt
- Full remote, async-friendly
- $108,000 – $130,000 base salary
- Direct access to customers from week one — you will hear unfiltered feedback about what you build
- We don't do post-mortems on failures with blame — we do them with curiosity
Job Type
Full-time
Level
Senior
Language
English
Salary Range
$108,000 – $130,000
AI Expertise
NLP & Prompt Engineering
Ready to apply for this role?
Create a free talent account in under 2 minutes.
- Apply to verified AI companies
- Get AI-matched job recommendations
- Message hiring managers directly
- Build your public AI talent profile