Founding Engineer (Data Science & Applied ML)

About Kita

In emerging markets, credit infrastructure is broken. Lenders rely on messy documents, fragmented borrower communication, and manual review

Kita is the AI platform for global lending operations. We automate loan origination, application completion, document verification, and credit review for lenders in markets where underwriting is still trapped in messy documents and manual follow-up — from the Philippines and Mexico to the US. Kita’s AI credit officer works directly with borrowers over WhatsApp, Viber, SMS, and email to collect missing information, resolve inconsistencies, and keep applications moving, while our AI underwriter extracts fraud-checked data and localized risk signals from chaotic financial documents to support faster, higher-quality credit decisions. The result is a more complete application pipeline, dramatically lower manual review burden, and a lending operation that moves faster without compromising risk.

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.

The opportunity

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.