Ts. Razeen Iqbal / Data Engineer & AI Solutions Engineer
I follow curiosity.Then I build
I build data pipelines, AI systems, products and experiments.
I started in civil engineering, moved into data, and found my way into AI. Now I build systems, products and experiments around problems I want to understand better.
Open to opportunities. Data engineering and AI roles, project collaborations, and talks.
Selected credentials
View all →
//Currently
Working on
- Data Engineering
- AI Systems
- Agentic Workflows
Building
Exploring
- Data + AI Products
- 3D Data Experiences
- Better Developer Tools
01 /Selected builds
Four builds.Four starting points.
Everyday problem → Real product
VSB
A Malaysian social-volleyball platform where organizers create sessions and players discover games, see who is playing, book places and take part in a community.
789 eachStrings, English and Malay15 of 15Tables with row-level security12 hUnpaid place heldActive · LiveCase study →
Work problem → Engineering tool
FORMA
A visual data workbench that makes the path from messy input to a reliable pipeline easier to see, work with and reproduce, while keeping engineering control.
1,001Rows in (example run)985Ready16Held for reviewActiveCase study →
Curiosity → Experiment
Sepang Vision Lab
A 3D, broadcast-style replay of the 2026 Sepang weekend: all five sessions rebuilt from public OpenF1 data, with 22 cars driving an aligned 3D model of the circuit.
5 (FP1 to Race)Sessions22Cars5.543 km / 15 turnsCircuitActive · LiveCase study →
Social experience → Game
Balang
A Malaysian probability party game: read the jar of 25 kuih tokens, bet on secret prediction cards, and play friends in peer-to-peer rooms with no backend.
25Tokens per round12Prediction card types0Backend serversActive · LiveCase study →
02 /Path
The path changed.The way I think did not.
03 /Featured work
Turning data quality checksinto a reviewable workflow.
QualityPlusProfessional work at AEM Energy SolutionsProof of concept
Rules score the data, AI suggests fixes, and a person approves every change.
| Well IDUnique | StatusComplete | Lift typeIn reference list | Depth (m)Range 0 to 6,000 |
|---|---|---|---|
| W-101 | ACTIVE | ESP | 2,140 |
| W-102 | ACTIVE | GL | 1,880 |
| W-102 | SUSPENDED | ESP | 2,010 |
| W-104 | blank | GL | 1,960 |
| W-105 | ACTIVE | ESPP | -420 |
DeterministicRules run the same way every time. 16 of 20 cells pass: 80%.
Illustrative sample data · not a QualityPlus capture
Demonstrated at the SPE AI Summit
Read the case study04 /Sharing
Learning is betterwhen I can pass it on.
Gemini Enterprise for AutomotiveMARii
Structured training
Cloud Essentials untuk SUK Perak
Structured training
Google AI Build 2025Universiti Putra Malaysia
Technical sharing
AEM Internal Technical Training
Internal knowledge sharing
- Understand
- Demonstrate
- Practise
- Apply
06 /Life
Away from the screen.
Running
94 outdoor runs · 548 km- 5K best
- 38:51
- 7:46 /km
- 10K best
- 1:28:35
- 8:52 /km
- Half best
- 3:20:05
- 9:29 /km
Volleyball
- Play
- People
- Coordination
- VSB
Formula 1
- Interest
- Questions
- Data
- Experiment
- Sepang Vision Lab
07 /Contact
Have somethingworth building?
Have an idea, project, opportunity, or interesting problem?
Open to opportunities. Data engineering and AI roles, project collaborations, and talks.