01Loan Labs
Agentic AI
Lois — Agentic Mortgage Workflows
LangGraph-powered agent system on Amazon Bedrock AgentCore for document processing and lender policy validation
-85%DOCUMENT CYCLE TIME
LangGraphAmazon BedrockAgentCore RuntimePython+4
AI Product Engineer
Ideas into products. Curiosity into work.
I've built and scaled two AI product teams at Finally and Loan Labs, and I care about the whole journey: the idea, the design, and why someone chooses it.
AI · startups · fintech · philosophy · chess
Currently building at Loan LabsPreviously Finally · Virginia Tech
Experience.
From research to real-world products.
Loan LabsApplied AI EngineerJan 2026 – Present
- Building Lois at an early-stage mortgage technology startup for internal and pilot workflows.
- Re-architected Lois from one-off Ruby LLM calls into a LangGraph agentic system on Amazon Bedrock AgentCore for mortgage-document classification, lender-specific renaming, and policy validation.
- Built agent-facing Rails APIs, borrower email intake, and an in-product conversational interface so users could handle loan documents and initiate agent actions in LoanOS.
- Designed fail-closed authorization for Composio integrations: tenant/owner scoping, separate write/send/merge/archive permissions, reviewed tool allowlists, and execution-time checks that invalidate revoked access.
- Connected CRM and document workflows across Google Drive, Box, Salesforce, HubSpot, Pipedrive, OneDrive, and SharePoint with fine-grained access controls and blocked delete actions.
- Introduced an AI-assisted software delivery workflow linking Linear/Notion product context, technical specifications, shared company knowledge, and senior-engineer code review.
FinallyAI Product Engineer / Tech LeadFeb 2024 – Jan 2026
- Joined as Finally’s first AI Product Engineer and led a three-engineer team that took Classify AI from prototype to production; built an LLM-assisted bookkeeping workflow processing 50K+ daily transactions and reducing manual categorization by ~80%.
- Designed a retrieval-augmented transaction-classification system using LangChain, Pinecone, Elasticsearch, Redis, Celery, Django, and W&B; combined semantic transaction history, merchant enrichment, and custom charts of accounts for bookkeeping recommendations.
- Evolved Classify AI from CSV upload to automated bank-data ingestion with Plaid/Teller, OCR-supported statement processing, reconciliation checks, and QuickBooks push; helped reduce first-month close time from 4+ months to ~2 weeks.
- Architected reusable banking infrastructure for account linking, token lifecycle management, encrypted access-token storage, webhooks, transaction synchronization, statement retrieval, and provider-normalized account data.
- Built cash-based underwriting for Finally’s corporate-card product using 90-day bank data, daily-balance reconstruction, Z-score logic, weekly recalculation, audit history, notifications, and manual-override controls. Underwrote $3M+ in credit for 50+ companies in approximately three months.
UNAR LabsMachine Learning EngineerJun 2023 – Aug 2023
- Developed accessibility-focused backend and data pipelines for visually impaired users using OpenCV, PyTorch, Transformers, FastAPI, Docker, GCP, and Hugging Face.
- Architected and optimized data pipelines for preprocessing, model training, and inference.
- Deployed scalable ML solutions on GCP with Docker containerization and Hugging Face model integration.
OutreachMachine Learning Platform Engineer InternMay 2022 – Aug 2022
- Built reusable NLP inference and deployment infrastructure with PySpark, MLflow, ONNX, NVIDIA Triton, Docker, Go/Python microservices, CI/CD, and GKE.
- Developed PySpark + MLflow pipelines for text processing and served ONNX models on NVIDIA Triton.
- Built Golang/Python microservices with Docker, unit tests, and CI/CD.
Selected Work · Interactive Portfolio
Featured Projects & Deep Dives.
Click any card to inspect the real-world impact, architecture, metrics, and technical write-up.
02Finally
Fintech
Classify AI — 50K+ Daily Transaction Engine
Hybrid semantic retrieval and LLM-assisted categorization reducing manual bookkeeping by ~80%
50K+TRANSACTIONS / DAY
PythonDjangoLangChainPinecone+5
03Finally
Fintech
Cash-Based Underwriting Engine
Real-time credit risk modeling using 90-day bank balance reconstruction and volatility scoring
$3M+CREDIT UNDERWRITTEN
PythonDjangoPostgreSQLRedis+5
04Virginia Tech
EdTech / Research
Gurukul — LLM CS Education & Master's Thesis
Adaptive learning environment with Socratic guardrails and RAG (Virginia Tech M.S., 130+ citations)
130+ACADEMIC CITATIONS
PythonFastAPITransformersLangChain+4
05Finally
Fintech
Reusable Banking Infrastructure
Encrypted token lifecycle, Plaid/Teller webhooks, and provider-normalized transaction sync
50+BUSINESSES CONNECTED
PythonDjangoPostgreSQLPlaid API+4
06UNAR Labs
ML Systems
Accessibility ML Vision & Speech Platform
Computer vision and NLP data pipelines for visually impaired users deployed on GCP
<150msPROCESSING LATENCY
PythonPyTorchOpenCVTransformers+4
07Outreach
ML Systems
NLP Inference & Triton Serving Platform
High-throughput ML platform using PySpark, MLflow, ONNX, and NVIDIA Triton on GKE
<20msINFERENCE LATENCY
PythonGoPySparkMLflow+5
How I Think & Build
Engineer’s rigor, product instincts.
Click any discipline to inspect what I use with my Claude Code & Codex setup, my engineering workflows, and direct backlinks to my work.
01Inspect setup ↗
Engineering
Production apps, resilient APIs, agentic orchestration, and CI/CD that ships.
LangGraphBedrock AgentCoreDjangoFastAPIRailsNext.jsDockerKubernetes
02Inspect setup ↗
Product
MVP scoping, spec-driven engineering, and user metrics tied to measurable outcomes.
Linear-to-CodeSpec DecompositionUser ResearchA/B TestingOKRsHuman-in-the-Loop
03Inspect setup ↗
AI & Analytics
RAG, hybrid semantic search, predictive models, and telemetry from data to deploy.
PineconeElasticsearchLangChainLangGraphBedrockW&BPyTorchTriton
04Inspect setup ↗
Strategy
Cash-flow risk modeling, underwriting algorithms, ROI, and stakeholder alignment.
Cash-Based UnderwritingRisk ModelingZ-Score VolatilityUnit EconomicsRoadmaps
Let’s work together
Something worth
building?
I’m interested in product engineering, applied AI, and founding engineering roles. Especially with people who care about how a product is built, experienced, and brought to market.
Let’s talk