Redwan Rahman
Backend AI Engineer & Computational Researcher
Engineering reliable, resource-aware AI systems and specialized compute pipelines. My work bridges the gap between production-grade artificial intelligence, spanning advanced reinforcement learning implementations and high-performance retrieval-augmented architectures, with scientific data processing workflows. Supported by a structured, verified foundation in cloud computing framework infrastructure, deep learning model optimization, and scalable API design, I focus on building resilient pipelines that translate complex intelligence models into stable engineering environments.
Systems Matrix
Featured Engineering Architectures
RAPCG-MetaRL
Resource-Aware Procedural Content Generation via Meta-Reinforcement Learning
A research framework for procedural content generation that integrates live hardware telemetry into reinforcement learning reward functions, enabling resource-aware training on consumer hardware. The system extends PPO, A2C, MAML, and RLHF with algorithm-agnostic reward shaping, fast task adaptation, and human preference alignment. It includes a containerized local deployment pipeline, Streamlit dashboard, reproducible experimentation tools, and supports Zelda and Sokoban environments for end-to-end PCGRL research.
Astro-AI
AI-Assisted Galaxy Evolution Analysis Platform
A modular astronomy research platform that combines AI-assisted scientific analysis with modern astrophysical workflows. Astro-AI integrates LLM-powered question answering, TF-IDF document retrieval, 21cmFAST cosmic evolution simulations, JWST spectral analysis, and Bagpipes SED fitting into a unified Streamlit application, enabling context-grounded exploration and interpretation of galaxy evolution data.
Blended AI
OBE-First Retrieval-Augmented Learning Platform
An Outcome-Based Education (OBE)-first AI learning platform that grounds every response in course materials through hybrid retrieval and curriculum-aware generation. Blended AI combines BM25 and semantic search, CO/PO-aware reranking, LLM-powered question answering, persistent student memory, and learning analytics to deliver explainable, citation-backed, outcome-aligned educational assistance for higher education.
Capabilities Matrix
Quantified Skill Footprint
Academic Performance Profile
Coursework strength by domain across the BSc in CSE
Technical Competency Radar
Professional development across AI engineering and full-stack domains
Operations Log
Professional Commit History
Backend AI Engineering Intern at FlyRank
July 2026 - PRESENT- Designing API contracts, retrieval-backed answer flows (RAG), and structured-output pipelines built to survive production-level environments.
- Implementing comprehensive evaluation harnesses, verification rubrics, and automated audit trails to benchmark model accuracy and failure modes.
- Configuring resilient tool-calling workflows and agent execution matrices across HTTP backends using robust error-handling policies.
Artificial Intelligence Intern at CodeAlpha
April 2026- Developed an NLP-powered support bot leveraging advanced natural language processing techniques for automated customer query handling.
- Built a multi-language translator integrating Google Translate and Azure Translator APIs for seamless cross-language communication.
- Engineered a symbolic music generation pipeline using LSTM networks; exposed via a CLI and a FastAPI dashboard for job execution, live logs, and output management with fully passing GitHub Actions CI workflows.
Mentor at QBangladesh
August 2025 - PRESENT- Mentored QSilver31 workshops with 100+ global participants teaching Qiskit programming, achieving a 95% completion rate.
- Delivered outreach increasing quantum technology awareness among Bangladeshi and international students.
President (Student Forum) at DIU Astrophysics Center
March 2025 - PRESENT- Led 270+ members, organizing 5+ technical events on computational astrophysics, gravitational wave analysis, and space science.
- Managed cross-functional teams for collaborative research in galaxy evolution, JWST data analysis, and astronomical machine learning.
Core Capabilities
Development & Research Toolkit
RAG & Retrieval Systems
Hybrid Search (BM25 + Vector), LlamaIndex, ChromaDB, Qdrant, Citation & Evaluation Pipelines
LLM Backend & Agents
FastAPI Tool Calling, Structured Outputs, Agent Execution, RAG Flows, Production Error Handling
Reinforcement Learning
PPO, MAML Meta-RL, RLHF, Resource-Aware Rewards, PCG (Zelda & Sokoban)
Scientific AI Computing
21cmFAST Simulations, Bagpipes SED Fitting, JWST Spectral Analysis, Astrophysics Pipelines
AI Application Stack
Streamlit Dashboards, FastAPI Backends, React/Flutter, Persistent Memory, Learning Analytics
MLOps & Experimentation
Evaluation Harnesses, Docker, GitHub Actions CI/CD, Hardware Telemetry, Reproducible Training
Generative Models
LSTM Music Generation, Sequence Modeling, PyTorch Training Pipelines
Credentials Log
Verified Certifications
Knowledge Sync
Selected Workshops & Bootcamps
BeginPlay Unreal Engine Indie Sessions Workshop
ORGANIZER: Untold GamesQBarsaat 2025: Quantum Machine Learning
ORGANIZER: QWorld & QPakistanData-Driven Astronomy Workshop
ORGANIZER: DIU Astrophysics CenterSummer School on Astrophysics 2025
ORGANIZER: CAM-SUSTAcademic Path
Education Matrix
BSc in Computer Science and Engineering
Daffodil International University (June 2022 - June 2026)
Recent Performance Indicators (Semester 9 Summer 2025):
Challenges
Competition Finalist Indexes
DIU AI Project Competition
Take Off Programming Contest
Unlock The Algorithm
Orange Corner Ideation
Hult Prize Finalist
Curriculum Vitae
Access full verified academic metrics, research listings, and software experience profiles.