The Role
Design, build, and deploy ML systems that link extracted document features to repayment and fraud outcomes. Run backtests, build evaluation and QA frameworks, develop adaptive/online learning for fraud and credit risk, and collaborate with customers to integrate models into underwriting workflows.
Summary Generated by Built In
About Kita
The Role
Compensation
In emerging markets, credit infrastructure is broken. Credit bureaus are unreliable, open finance is limited, and most financial data lives in messy documents. As a result, millions of individuals and businesses are locked out of credit because lenders can’t properly assess them.
Kita is building the infrastructure to fix this. We turn messy financial documents into structured, fraud-checked signals that lenders use to make underwriting decisions. We work with customers ranging from fintechs to enterprise banks, and build closely with them on the ground — during the YC batch, we spent time in Manila, Singapore, Jakarta, and Mexico City.
We’re a Stanford AI team backed by Y Combinator, top funds, and leading angels across Silicon Valley and Southeast Asia. During the YC batch, we grew ~40% week-over-week with customers across three continents. Our CTO was ranked #1 in Stanford CS in 2025.
Kita is seeking a Founding Engineer, Data Science & Applied ML to build the intelligence layer that makes our products useful for lenders. This is a technical role at the intersection of machine learning, data science, credit risk, and product engineering.
You will design and run backtests on historical lending data, identify which document-derived signals are predictive of repayment and fraud risk, and build evaluation systems that improve model performance in live underwriting workflows. You will also help shape new product offerings across the lending stack by tying extracted features and model outputs to real financial outcomes.
What you’ll be working on
As a founding engineer, you will design, build, and deploy ML systems that improve credit decisioning, fraud detection, and underwriting workflows. This means leading product from ideation to production, including scoping, implementation, deployment, and iteration of vision and VLM-based underwriting systems by linking extracted features to repayment outcomes.
- Design and run backtests to evaluate the predictive value of extracted financial and fraud signals
- Benchmark and build evaluation frameworks for validation, error analysis, and QA in high-stakes financial settings
- Develop adaptive and online learning approaches to strengthen fraud and credit risk signals over time
- Work closely with customers to understand underwriting workflows and translate them into robust ML systems
Requirements
- 3+ years of experience building and deploying ML software in production
- 2+ years of experience in analytics, risk, fraud, or credit domains in industry
- Strong background in machine learning, data science, RL, statistics, quantitative engineering, & applied ML
- Strong full stack software engineering ability and experience building production systems end to end
We are looking for a fast-learning, eager-to-build founding engineer with experience in credit risk, lending, underwriting, fraud, or fintech. Experience with computer vision or multimodal ML systems is a strong plus, as is experience with model calibration, feature selection, and error analysis in high-stakes settings. This is a highly applied, forward-deployed role. At Kita, you will help define the product foundations of the company from the ground up.
The base pay range for this role is $150,000 – $220,000 per year.
Skills Required
- 3+ years of experience building and deploying ML software in production
- 2+ years of experience in analytics, risk, fraud, or credit domains in industry
- Strong background in machine learning, data science, RL, statistics, quantitative engineering, and applied ML
- Strong full stack software engineering ability and experience building production systems end to end
- Experience with computer vision or multimodal ML systems
- Experience with model calibration, feature selection, and error analysis in high-stakes settings
- Experience working with credit risk, lending, underwriting, fraud, or fintech customers
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
Kita is an AI-native credit infrastructure platform that automates credit review for lenders in emerging markets. It leverages vision language models (VLMs) to transform unstructured borrower documents—such as bank statements and e-wallet records—into fraud-checked, decision-ready data. By automating document verification and underwriting, Kita enables lenders to scale operations and improve financial inclusion while keeping final credit decisions in the hands of human teams.
