Tai Lin
Resume ↓ Read the chapters →

Tai Lin

Founding Engineer · AI Infrastructure · Capital Markets

Available for consulting A note about the author →

I find meaningful problems to solve from 0 to 1 while wearing multiple hats. This is how I think about building products ↗

HighFi

Founding Software Engineer

Mar 2023 – Present

  • TypeScript
  • PostgreSQL
  • Next.js
  • Vercel AI SDK
  • Pulumi
  • GCP

$350K

ARR scaled

HighFi is agentic capital markets infrastructure — replacing manual, operations-heavy back-office workflows with intelligent, self-serve systems for lenders and asset managers. As founding engineer and primary technical customer contact, I built the platform's core systems end-to-end and scaled HighFi's first two enterprise customers from $0 to $350K ARR.

Capital Markets OS Ch. II →

Purpose-built operating system for the compliance, servicing, and reporting layer between a legal agreement and a funded transaction. Six components, one config registry — onboarding is a config task, not a sprint.

6 components, config-driven
AI Agent Harness Ch. III →

BaseAgent<TDeps,TInput,TOutput> powering 6+ agents with typed dependency injection, structured step tracing, and per-step Slack observability. Stateful FSM design.

6+ agents in production
Millie & Penny Ch. IV →

Capability-gated agents resolving authorized toolsets per request. Millie executes funding draws and SOFR updates in Slack. Penny streams amendment edits from a mode-scoped in-app panel.

5 capabilities, authorized per request
The Night Agent Ch. V →

Three-stage Claude Code pipeline on GitHub Actions. Safety enforced below the prompt layer — every shell command routes through a whitelist. Specs written by day, PRs reviewed at 8 AM.

55m total pipeline budget

Utradea

Software Engineer → Software Engineer II

Mar 2021 – Feb 2023

Ch. VI — Before HighFi →
  • Node.js
  • MongoDB
  • PostgreSQL
  • AWS ECS
  • Redis
  • OpenAI API

50+

APIs migrated

Utradea, now Financial Modeling Prep, is a market data platform serving free and enterprise API tiers to developers worldwide. I joined as the first engineering hire with no formal CS background — self-taught and shipped paid production features within months. I built Stripe payments and the SEC Dashboard, and re-platformed the MERN backend from Lightsail onto ECS with Fargate to support 50+ production APIs — work I believed in enough to become a shareholder.

FMP API Migration

Led post-merger migration of 50+ Financial Modeling Prep APIs into Utradea's Node.js / MongoDB stack — owned the full infrastructure transition.

AWS Infrastructure

Re-platformed from Lightsail onto ECS with Fargate and load balancers; multi-node Redis cycle caching with subscription-tier rate limiting for high-frequency price reads.

First AI Feature

Piloted an early OpenAI API integration powering Financial Writer — an AI-generated news article tool on real-time market data, shipped before ChatGPT made this obvious.

SEC Dashboard & Stripe

Built the SEC Dashboard end-to-end — an NLP pipeline (winkNLP, VADER) parsing 8-K filings into investor-readable insights. Integrated Stripe for Utradea's first paid users.

BMO Financial Group

Business Analyst → Senior Business Analyst

May 2018 – Mar 2021

Ch. VI — Before HighFi →
  • Requirements
  • Systems Analysis
  • Regulatory Compliance

3yr

Domain depth

Vendor Risk Decommissioning

Led decommissioning of a vendor risk management platform — owned business requirements and migration to a streamlined in-house replacement.

Credit Flow Transformation

Defined E2E requirements and drove cross-functional delivery for the Credit Flow for Commercial Banking transformation.

Client Portal Integration

Owned E2E Client Portal Integration — streamlined business banking onboarding from prospecting to signing across legacy systems via API, enhancing Online Banking for Business across platform teams.

Compliance Reporting

Introduced configurable credit compliance reporting templates scaled across multiple lines of business to standardize regulatory workflows.

Creative Destruction Lab

Venture Growth in Machine Learning Stream

2017 – 2018

Ch. VI — Before HighFi →
  • ML
  • Venture
  • University of Toronto
ML Venture Cohort

Worked alongside ML-native founders and operators during the early commercial wave of machine learning. Developed early conviction: the bottleneck is infrastructure, not capability. B.Com, University of Toronto.