Founding Engineer
AI summary of the role
Founding engineer at Kita, a fintech startup expanding credit access globally.
What you’ll do
- Build agentic workflows that collect borrower files via WhatsApp, Viber, SMS, and email, chase missing info, reconcile mismatches, run financial analysis, and produce decision-ready assessments
- Harden LLM-based systems for production: evals, failure modes, latency/cost at volume, graceful degradation
- Ensure auditability and traceability of every number to its source for regulators, auditors, and credit committees
- Implement security measures for regulated lenders handling borrower data and help clear reviews
What you’ll bring
- Production experience with LLM-based systems including hallucinations, drift, evals, versioning, and cost
- Strong backend fundamentals; Python and TypeScript are daily drivers
- Ability to operate in ambiguity and turn vague problems into plans
- Research and build in the same motion; stay ahead of the field
Technologies
LLM · Python · TypeScript · WhatsApp · Viber · SMS · computer vision · evals · agentic workflows
Source and classification
Internal deployment & tooling · Evidence for this classification:
The role Credit is the difference between a business that grows and one that doesn't, a family that absorbs a shock and one that doesn't. Kita decides who gets assessed fairly and how fast. That is the scale of what you'd be working on: not a metric on a dashboard, but whether capital reaches people it has never reached before, in five countries and counting. You'll build the agentic systems that do the underwriting work, harden them until they hold up under enterprise volume and regulatory scrutiny, and work directly with the founders on what gets built next. What you'll work on Agentic workflows that run the full assessment: collecting a borrower's file across WhatsApp, Viber, SMS, and email, chasing what's missing, reconciling what doesn't match, running the financial analysis, and producing a decision-ready assessment Hardening. Getting these systems from working to reliable is
More from the job description
The role Credit is the difference between a business that grows and one that doesn't, a family that absorbs a shock and one that doesn't. Kita decides who gets assessed fairly and how fast. That is the scale of what you'd be working on: not a metric on a dashboard, but whether capital reaches people it has never reached before, in five countries and counting. You'll build the agentic systems that do the underwriting work, harden them until they hold up under enterprise volume and regulatory scrutiny, and work directly with the founders on what gets built next. What you'll work on Agentic workflows that run the full assessment: collecting a borrower's file across WhatsApp, Viber, SMS, and email, chasing what's missing, reconciling what doesn't match, running the financial analysis, and producing a decision-ready assessment Hardening. Getting these systems from working to reliable is most of the job: evals, failure modes, latency and cost at volume, graceful degradation when a model or an upstream system misbehaves Auditability and traceability. Every number we return has to trace back to its source and survive a regulator, an auditor, and a credit committee. This constraint shapes the architecture, it isn't bolted on Security. Our customers are regulated lenders handling borrower data. You'll build to that bar and help us clear the reviews that come with it Integrations [... source excerpt omitted ...] me motion. New capability lands, you've already tested whether it changes what we should ship Genuinely curious about the whole company. Our engineers sit in on sales calls, read customer contracts, and work closely with our customers to understand how they make decisions You operate clearly in ambiguity. Not tolerate it, operate in it: you can take a vague problem, find the real constraint, and come back with a plan Production experience with LLM-based systems and the aftermath, including hallucinations, drift, evals, versioning, and cost Strong backend fundamentals. Python and TypeScript are our daily drivers, but how you think matters more than what you've used All in on [... source excerpt omitted ...] r regulated-industry work Computer vision on messy real-world documents Spanish, Tagalog Why this one Very few engineering jobs move real capital to real people at this scale. You'll also see it: our team travels to the markets we serve, and you'll sit with the credit officers in Manila and Mexico City using what you shipped. Benefits: competitive salary and meaningful equity, relocation support, health coverage, international travel across our markets, offsites, team gym sessions, and a lot of good food. Compensation The base pay range for this role is $160,000 – $220,000 per year.
Employer postings · Data from · Sources