Pearson Edexcel A Levels
Private Candidate
Studying Physics, Mathematics, and Further Mathematics independently as a private candidate.
Physics
Mathematics
Further Mathematics
Based in Dhaka, Bangladesh
AI & Machine Learning Developer
Currently studying Pearson Edexcel A levels · Open to AI/ML internships
I build practical AI systems — agents that call tools, computer vision pipelines that run on limited hardware, and full-stack apps that actually get used. Most of my work sits at the intersection of models and real systems: FastAPI backends, edge inference, and agents that stay grounded in data instead of making things up.
Selected Work
Full-stack AI agent for a laptop repair shop. Technicians create tickets and logs; customers chat with an assistant that answers only from real repair data via Mistral tool calling. Streaming responses, JWT auth, and deliberate guardrails against hallucination.
Added a Mistral-powered assistant to a Flask school management platform so teachers can query student data in natural language. Built secure tool-calling functions over SQLAlchemy/SQLite that respect role-based access instead of exposing the whole database.
Multimodal agent that can control a Linux desktop (Wayland) on machines with only 4GB RAM. Uses in-memory frame capture and kernel-level scancode injection so it can see the screen and type/click without heavy dependencies.
Capabilities
Languages & Frameworks
AI / ML
Backend & Data
Systems
Academic background
Private Candidate
Studying Physics, Mathematics, and Further Mathematics independently as a private candidate.
Background
I'm a self-taught AI developer from Dhaka who got into machine learning the hard way — through rigorous independent study in differential calculus, linear algebra, and probability, specifically applied to how neural networks actually work under the hood.
I don't build demos. I build systems that run under real constraints: limited RAM, free-tier cloud, low-power edge hardware. That discipline shapes everything — from how I architect APIs to how I think about model quantization.
Currently looking for an internship where I can contribute to production-grade AI infrastructure, learn from experienced engineers, and push further into agentic and multimodal systems.
Let's connect
I'm actively seeking internship opportunities. If you're working on something interesting in AI, vision, or intelligent systems — reach out.