AI ENGINEER · SYDNEY, AUSTRALIA

Bisar UlHasan

I build AI products end-to-end — from first prototype to a system running in production. I help founders turn an AI idea into something that ships.

Book a call See my work

Focus: AI products · 0→1
Stack: LLMs · RAG · Agents
Now: Available for projects

SCROLL

LLMs/RAG Pipelines/Multi-agent/LangGraph/LangChain/MCP/Vector Search/Fine-tuning/FastAPI/PyTorch/Evaluation/Prompt Engineering/Vercel/Supabase/Docker/Python/LLMs/RAG Pipelines/Multi-agent/LangGraph/LangChain/MCP/Vector Search/Fine-tuning/FastAPI/PyTorch/Evaluation/Prompt Engineering/Vercel/Supabase/Docker/Python/

01 / About

I take AI products from prototype to production.

Founding engineer0→1 builderProduction-gradeShips fast

I am an AI Engineer in Sydney who builds production AI products end-to-end — LLMs, multi-agent systems, RAG, and the data pipelines underneath them. I was a founding engineer at a speech-AI startup, where I led the engineering team as it grew from a small founding group into a full company, shipping production text-to-speech for enterprise clients.

Today I drive AI adoption inside an organisation, where the work is judged not by demos but by systems people depend on every day. The throughline is the same: take an AI idea, build it properly, measure it, and put it into production.

02 / Work with me

Got an AI product to build? Let's ship it.

I work with founders and teams who want real AI in their product — working in production, not just in a demo.

Scope

We pin down the highest-value thing to build and agree on what “good” looks like.

Build

I design and build the system end-to-end: data, models and LLMs, evaluation, and the product around it.

Ship

It goes live with quality measured, and your team able to run it.

Best fit: founders and SMBs with an AI idea — or a half-built one — that needs to actually work.

Book a call

03 / Work

Real systems, shipped.

Problem, build, outcome — no fluff.

RAG / PRODUCTION01

Teaching Assistant Bot

Problem: Staff needed fast, trustworthy answers from a large, messy body of school documents, without sending anything to a third-party cloud.
Built: A production RAG system with hybrid retrieval, cross-encoder reranking, citation enforcement, and a CI-gated evaluation pipeline so quality is checked on every change. Runs locally on open-source models with a cloud fallback.
Outcome: Source-cited answers people can trust, with retrieval quality measured on a golden evaluation set rather than guessed at.

PythonLangChainWeaviateOllamaCohereRAGASGitHub Actions

View on GitHub

DOCUMENT AI02

Teaching Program Automation

Problem: Writing teaching programs across the school's full subject list was slow, repetitive, and ate weeks of staff time.
Built: An AI document-processing pipeline that drafts programs from source material and structures them to the required format, leaving staff to review rather than write from scratch.
Outcome: Turned a multi-week manual job into a review-only workflow, across the whole subject list.

PythonPlaywrightLLMs

MULTI-AGENT03

Meeting Minutes Pipeline

Problem: Turning raw meeting transcripts into clean, formatted minutes by hand was tedious and easy to get behind on.
Built: A three-agent pipeline — transcript processor, minutes writer using Anthropic tool calling, and document generator — exposed via a FastAPI webhook with async background execution.
Outcome: Raw transcripts become formatted Word minutes automatically, with a person only in the loop to approve.

PythonFastAPIAnthropicMulti-agent

DATA PRODUCT04

NAPLAN Analytics Platform

Problem: Raw national-assessment results were hard to turn into decisions, and analysing them by hand took weeks.
Built: A web platform that turns raw assessment exports into interactive dashboards for school-wide decisions, plus personalised practice that targets each student's weakest skills.
Outcome: Collapsed weeks of manual analysis into a near-instant view, and made the data usable by people who are not analysts.

ReactVercelSupabasePostgreSQLEdge Functions

04 / Testimonials

What people I've led and worked with say

It was an amazing experience to have Bisar as my team lead. He is an exceptional individual who can lead the team towards its goals. During his time at Scribe Audio he introduced his team with various tools and technology stacks which accelerated the operations.

Syed Haider Ali Zaidi

Building AI Platform @ Enmacc

Reported to Bisar directly

Read them on LinkedIn →

05 / AI focus

How I build AI that ships

Start from the boring, repetitive work

The best AI wins are not flashy. They are the slow, manual tasks people do every week. Find one, automate it well, and the value is obvious.

Measure it or it does not count

An AI system you cannot evaluate is a demo. Build the evaluation set, gate quality in CI, and you can ship changes without crossing your fingers.

Keep a person in the loop where it matters

Automation should draft and propose. People approve. That split is what makes AI safe to put in front of a real organisation.

Let's build your AI product.

If you're a founder or team with an AI product to build — or an idea that needs to become one — I'd like to hear about it. Available for select projects now.

Book a call bisar1000@gmail.com

in/bisarhasan bisarulhasan @bisarulhasan @bisarhasan