Forward Deployed Full Stack Engineer

Posted yesterday

kaajEl Paso (TX)

Software Developers Custom Computer Programming Services

SENIORITY

Senior

SALARY

$100,000-$150,000

Apply

About the role

About KaajKaaj is the underwriting OS for small business lending, an agentic AI credit intelligence platform that turns messy borrower packages into decision-ready credit analysis in minutes, not days. Founded in 2024 in San Francisco by operators from credit, fraud, risk, and AI systems (Uber, Cruise, Amex, Varo Bank), Kaaj raised a $3.8M seed round led by Kindred Ventures. The platform has processed $15B+ in loan originations across equipment finance lenders, SMB lenders, banks, MCA and revenue-based finance funders, and brokers.

The Role: We are hiring a talented Forward Deployed Full Stack Engineer, a senior IC who owns the full technical relationship with lender and broker customers while shipping production code across the platform. This is not a solutions consultant who hands off specs, and it is not a backend engineer who never talks to customers. You will embed with credit operations teams, scope integrations against real LOS and CRM environments, debug production workflows alongside underwriters, and write the code that makes each deployment successful. Roughly 70% product engineering, 30% customer-facing technical work. You are the bridge between Kaaj's platform and the operational reality of commercial lending: shared inboxes, incomplete packages, mismatched business names, urgent broker emails, and policy exceptions that never fit a clean diagram.

Responsibilities: Product engineering

Build and extend the underwriting pipeline: email and document ingestion, classification, bank statement parsing, KYB/KYC, credit writeups, and CRM sync
Ship features on the borrower application portal (dynamic forms, e-signature, file upload, lender matching) and the lender underwriting dashboard (deal pipeline, KYB review, bank analysis, credit memo editing, integration configuration)
Optimize LLM-heavy paths — document extraction, agentic analysis, credit memo drafting — with attention to cost, latency, and reliability
Implement per-lender customization: sync configs, feature flags, credit memo templates, and workflow triggers
Integrate third-party services across document intelligence, identity/KYB, credit bureaus, e-sign, and web research Customer-facing technical work
Own technical onboarding for new lender and broker deployments: discovery, integration scoping, go-live, and hypercare
Configure CRM and LOS integrations — field mappings, custom objects, file uploads, lead conversion — in live customer environments
Debug production issues with customers: stuck workflows, parsing failures, CRM mismatches, extraction errors
Translate underwriting policy into code: matching criteria, memo templates, KYB thresholds, document requirements, exception rules
Gather product feedback from credit teams and brokers; prioritize and ship fixes that unblock deal flow

Tech Stack Backend: Python, FastAPI, async workers, PostgreSQLFrontend: React, Next.js, TypeScript, Tailwind Orchestration: Workflow engine for multi-step, fanout pipelinesAI/LLM: Multi-provider LLM gateway, prompt skills, agentic tool-calling, structured extraction Document intelligence: Cloud OCR, PDF parsing, classification Data: Azure PostgreSQL, Redis, object storage Integrations: CRM (Salesforce, Dynamics, Zoho, HubSpot), e-sign, credit bureaus, identity/KYB vendors Infra: Docker, CI/CD, Azure cloud services You will work across distributed services daily — API layer, workflow workers, frontend apps, and an LLM routing gateway — in a multi-tenant architecture where schemas, configs, and prompts are per-lender.

Qualifications:

2+ years of professional software engineering with meaningful full-stack ownership
Strong Python — async patterns, API development, SQL, production debugging
Strong TypeScript/React — Next.js, component libraries, client and server state
PostgreSQL fluency — complex queries, JSONB, performance tuning
REST API design — webhooks, authentication, idempotency, third-party error handling
Cloud experience — Azure preferred (Blob, managed Postgres, document intelligence); equivalent depth on AWS/GCP with willingness to ramp
Workflow orchestration — job queues, DAG workflows, or similar; retry semantics, timeouts, fanout patterns
LLM application development — prompt engineering, structured output, toolcalling agents; features shipped to production, not just experiments
Direct customer technical work — scoped integrations, sat on stakeholder calls, shipped code from what you learned
Clear communication — explain a parsing failure to a credit analyst and a field mapping issue to an IT admin in the same week
Comfort with ambiguity — requirements arrive as forwarded emails and spreadsheet screenshots, not Jira tickets

Why Work With Us:

Early engineering hire at SF-based startup with real revenue-paying customers
Competitive salary and meaningful equity as an early engineering hire (range: $100,000-$150,000)
Health insurance
Flexible PTO
Remote work with HQ in San Francisco
Direct access to founders and engineering leadership — no layers between you and technical decisions

Before you apply

Applying takes about a minute. These four things decide how fast it moves after that.

Your profile is current

It's what we read first. Occupations, seniority and locations matter more than a long history.

Two examples you can talk through

Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.

A number in mind

What you're on now and what would make you move. We negotiate better when we know both.

Your notice period

Employers plan around it, and it's the question that stalls offers most often.

Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.