AI engineer · Dhaka, Bangladesh
AI engineer working in Python and TypeScript. Three of my projects are public and installable: a Git safety CLI on PyPI, a CI compliance action on the GitHub Marketplace, and a multimodal debugging agent running on Hugging Face Spaces.
Available now · fully remote · ~20 h/week during term, full-time between semesters · open to junior AI/LLM roles, internships and scoped contract builds
Three public distribution channels. Each has its own packaging and review requirements. Each was cleared.
Approach / 01
Tool-calling agents where the interesting part is the interception layer — what the model is not permitted to do. Git Sensei blocks destructive repository operations before they execute rather than warning after. That layer, not the natural-language translation, is what the hackathon prize was for.
RAG where the basis for a decision is an authoritative document, not a regular expression. The Data Guardian judges whether support-ticket content is sensitive by retrieving over the written data-governance policy, and logs every redaction to an ES|QL dashboard so the decision can be audited afterwards.
SessionSolve does not stop at proposing a patch. It generates a Playwright regression test that shows the fix works. “LLMs write plausible code” is a fair objection, and the honest answer to it is evidence, not confidence.
Evidence / 01
Five projects, all public, all licensed. Every line is readable and three of them install or run without cloning anything.
Python CLI · published on PyPI · GPL-3.0
Prize winner — Code with Kiro Hackathon (Kiro AI, Devpost)
A natural-language Git assistant. You describe the outcome you want; it translates that into shell commands — and a guard layer intercepts destructive repository operations before they execute. Python with the OpenRouter API, packaged for PyPI so it installs with a single pip command.
The interesting part
The prize was for the interception, not the translation. “What stops the agent doing damage?” is the hardest question about LLM tool use, and it deserves a mechanism rather than a warning dialog.
GitHub Action · published on the GitHub Marketplace · MIT
Built for the Chrome Baseline Tooling Hackathon
A CI action that scans CSS against MDN Baseline compatibility data, posts an actionable policy report on every pull request, and blocks merges that break web-compatibility policy.
The interesting part
It is policy as code, in the merge path where it cannot be skipped. Structurally the same thing as an eval gate in an ML pipeline — take an external spec, turn it into a rule a machine enforces, then put the machine somewhere a human can’t wave it through.
Multimodal debugging agent · deployed on Hugging Face Spaces · MIT
Built for the Gemini 3 Hackathon
Give it a screen recording of a bug and the repository the bug lives in. It uses vision and a long context window to localise the fault, proposes a patch, and generates a Playwright regression test that verifies the fix visually.
The interesting part
Most demos stop at “proposes a patch”. This one closes the loop — perceive, localise, act, and then produce evidence the action worked.
Detects and redacts personally identifiable information in live support tickets. It judges sensitivity by retrieving over the written data-governance policy rather than pattern-matching alone, and logs every redaction to an ES|QL dashboard for audit.
The interesting part
Grounded decisions plus provenance. If you can’t show why something was redacted, you don’t have a compliance tool — you have a filter.
Renders live news and weather inside a strict 40×24 Teletext grid, with CRT shaders.
The interesting part
The aesthetic isn’t the problem — fitting arbitrary live content into a fixed 40×24 cell budget is. It’s a constraint-satisfaction engine wearing a UI costume.
Approach / 02
I'm looking for three things, in this order.
A junior AI/LLM engineering role or internship, fully remote. What I want most from a first job is real users and day-to-day code review.
Scoped contract builds — a defined deliverable with a defined end. The work I’m best at is turning a manual workflow into a tool that runs on its own.
Open-source collaboration. I contribute upstream as well as publish — I have two fixes merged and shipped in an open-source developer CLI I use daily. If something I’ve built is useful to you and it’s missing a feature, open an issue and I’ll read it.
Profile / 01
I'm Md. Rafi, a software engineering undergraduate in Dhaka, Bangladesh.
I started shipping LLM tooling in September 2025, and decided early that publishing to a registry — where installation is one command and anyone can read the source — is a different discipline from building a demo. It forces decisions you can skip otherwise: what happens on bad input, what the tool refuses to do, whether a stranger can run it without you in the room.
Four of these five projects began as hackathon entries. The deadline is a feature: it's the constraint that decides what the project actually is.
I plan to transfer to Universiti Tun Abdul Razak in Kuala Lumpur in late 2026, pending visa. My location changes; my availability doesn't. That's why the work I'm looking for is remote.
“Rafi Automation Systems” is the name I publish my work under. It's a name for the work, not a company with staff.
Record / 01
B.Sc. in Software Engineering · expected April 2029
CGPA 3.71 / 4.00 (3rd semester)
Transfer to Universiti Tun Abdul Razak (UniRazak), Malaysia — B.IT (Hons) — pending visa
Higher Secondary Certificate (Science) · October 2024 · GPA 4.92 / 5.00
Cambridge University Press & Assessment, 2026
Overall 186, CEFR level C1
Codecademy, 2025
Kiro AI, Devpost. For a CLI assistant that translates natural language into safe, context-aware Git syntax, with interception of destructive commands.
DIUSEC, Daffodil International University, 2025 · 5th overall, 4 problems solved
Native
Cambridge Linguaskill, overall 186 (CEFR C1)
Technical skills