Open to opportunities

AI Product Engineer building practical AI agents and automation systems

I design and build AI-powered workflows, backend APIs, voice agents, WhatsApp automations, and CRM systems for teams that want practical AI solutions, not just demos.

I help turn business problems into working AI products by understanding the workflow, finding the real bottleneck, designing the right product flow, and building systems that integrate with existing tools.

Contact Me View Work

About

I build AI systems around real business workflows

“
I work at the intersection of AI engineering, product thinking, and business workflow automation. I help teams understand what to build, why it matters, and how to ship it as a reliable system.

I work across product discovery, backend development, AI agent design, workflow automation, and CRM integration. I can help with AI agent development, voice AI agents, WhatsApp automation, CRM workflows, FastAPI backend systems, LangChain pipelines, LangGraph workflows, and LLM integration into existing tools.

Focus Areas

AI, automation, and backend
workflows I build

AI Agent Development

I build AI agents that can handle multi-step tasks, collect context, make decisions, and connect with tools like CRMs, databases, calendars, and messaging platforms.

Voice and WhatsApp Automation

I design conversational workflows for voice and WhatsApp. These systems can qualify leads, collect user requirements, answer common questions, and hand off context to human teams.

CRM Automation

I connect lead data, follow-up workflows, qualification logic, and sales operations so teams can act faster with better context.

Backend APIs

I build FastAPI and Python backend services that power AI-native products, automation systems, and internal tools.

Product Discovery

Before building, I map the workflow, understand the user need, identify the bottleneck, and define where AI can create real value.

AI Integration

I integrate LLMs into existing products, CRMs, dashboards, internal workflows, and business tools without forcing teams to change how they already work.

Selected Work

AI AUTOMATION PROJECTS AND
BACKEND WORKFLOWS I HAVE BUILT

All work

My role has been engineering owner of the TalkOps fork: deciding what to fix first

TalkOps Voice AI Agent Platform

Most teams that try to build a voice AI agent end up building five products at once. A telephony integration. A WebRTC layer for browser calls. An auth system. A place to store recordings. A background job queue so calls don't block the app. An admin panel to manage all of it. TalkOps exists so a team doesn't have to build all five from scratch. TalkOps is a commercial voice AI platform for building, deploying, and managing conversational AI agents, with both telephony and WebRTC support built in. It ships as a full-stack foundation: a Next.js frontend, a FastAPI backend, a PostgreSQL database, Redis-powered background tasks, dedicated audio storage, and a deployment structure that's ready for production rather than a demo.

Next.js 15React 19TypeScriptTailwind CSS+12

Details

Solo developer

Super Enrich

Upload a CSV of email addresses and get back company data: industry, headcount, funding, tech stack, whatever fields you ask for. Every value comes back with a source link and a confidence score.

Next.js 15React 19TypeScriptTailwind CSS+13

Details

Process

HOW I TURN WORKFLOW PROBLEMS
INTO AI SYSTEMS

Understand the workflow

I map the existing process before choosing tools or writing code.

Identify the real problem

I look for the actual bottleneck behind the request, not just the surface-level issue.

Design the AI product flow

I plan the system architecture, user flow, data flow, and AI touchpoints.

Build the system

I implement the workflow using clean backend code, AI pipelines, APIs, and automation tools.

Integrate with existing tools

I connect the system with CRMs, messaging platforms, databases, calendars, and internal tools.

Measure and improve

I review real usage, fix weak points, and improve the workflow over time.

Stack

TOOLS I USE TO DESIGN, BUILD,
AND SHIP AI PRODUCTS

I work across product discovery, workflow mapping, AI system design, backend development, automation, and delivery. These are the tools I use to move from problem understanding to working product.

Product and Workflow Planning

Tools I use to map workflows, define product requirements, plan features, collaborate with teams, and turn unclear business problems into structured product flows.

JiraNotionExcalidrawMiroFigmaGoogle SheetsSlack

AI and Automation

Tools I use to build AI agents, automate business workflows, qualify leads, connect systems, and create AI-powered user experiences.

LangChainLangGraphOpenAI APIn8nVoice AIWhatsApp APICRM Integrations

Backend and Data

Tools I use to build reliable backend services, API workflows, data models, integrations, and automation logic.

PythonFastAPIPostgreSQLDrizzle ORMREST APIsWebhooks

Frontend and Product UI

Tools I use to build clean product interfaces, internal tools, dashboards, and user-facing workflows.

Next.jsReactTypeScriptTailwind CSS

Case Studies

DEEP DIVES INTO PRACTICAL
AI WORKFLOW PROJECTS

All case studies

TalkOps Voice AI Platform — End-to-End Product Case

How I designed and built a commercial voice AI agent platform from scratch — from blank repo to white-label B2B product — covering system architecture, key product decisions, and the hard tradeoffs of building real-time infrastructure under commercial pressure.

Key insight

The real product was not the voice agent technology — competitors had similar capabilities. The product was the operational layer that made deploying and managing voice agents fast and repeatable. Whoever reduced deployment time from weeks to days would win the early market.

Read case study

Super Enrich: From Open-Source Scraping Demo to Multi-Provider Enrichment Tool

Super Enrich started as Fire Enrich, an open-source demo Firecrawl built to show off their scraping API. I forked it and spent the following weeks turning a single-user, single-provider demo into something that could run for real people: pluggable scraping and LLM providers, full authentication, and the security hardening a public tool needs that a demo never did.

Key insight

The gap wasn't AI quality. Fire Enrich's phased pipeline, each stage building on what the last one verified instead of asking one model call to guess everything at once, already produced solid extractions. The actual blocker was distribution: one provider pair, no concept of a user, no hardening for public traffic. That's a much smaller problem than "build a better enrichment engine," and it's the one I actually had to solve.

Read case study

Contact

Let's work together

Have a workflow problem, product idea, AI agent, or automation system you want to build? Send me a message. I can help you think through the workflow, design the right solution, and build a practical AI-powered system.

LET'S WORK
TOGETHER

Have a workflow problem, product idea, AI agent, or automation system you want to build? Send me a message.

Get in touch