Computer Science PhD Student | AI Systems for Distributed Systems & Networking | Backend Engineering
I’m Nieb Hasan Neom, a Computer Science PhD student and Kummer Doctoral Fellow building AI systems for distributed systems and networking. My work combines guarded LLM orchestration and agent-driven data movement with three years of backend engineering.
AI & Agentic Systems: LLM function calling and tool use · Schema-constrained generation · Agentic workflow orchestration · Ollama and Hugging Face models · PyTorch, Pydantic, and NumPy
Distributed Systems & Backend: Java and Spring Boot · Apache Kafka and message queues · Microservice and REST API design · AWS S3, SNS, and EC2 · PostgreSQL, MongoDB, Redis, and MySQL
Systems & Networking: Python, C, C++, SQL, and Bash · TCP performance analysis · Concurrency tuning and multiprocessing · Zero-copy sendfile() and Linux systems programming · CloudLab, FABRIC, and TACC/ACCESS
Engineering Tooling: Git and Gradle · Jenkins and Jira · IntelliJ IDEA, DataGrip, and VS Code · LaTeX · OpenAI and Google Gemini APIs
Researching machine learning for distributed systems and networking in the Computer Systems & Networking Lab with Dr. Md Arifuzzaman. Current work covers guarded scientific-model orchestration and bounded, telemetry-driven data-movement optimization.
As a backend engineer on a blockchain-based token-trading platform, I worked on trade, user, wallet, and fee-management services; introduced message queues for reliable inter-service communication; added caching to reduce response latency; and implemented two-factor authentication for sensitive trading operations.
Missouri University of Science and Technology
Khulna University of Engineering and Technology
A state-aware orchestration layer that extends LLM function calling with explicit workflow semantics so domain scientists can invoke trained prediction models through constrained natural language.
Backend service work for a blockchain-based token-trading platform, centered on reliable service communication, latency-conscious caching, and stronger controls for sensitive operations.
Undergraduate thesis research that contributed to a published hybrid recognition system combining image preprocessing, transfer learning, and a random-forest classifier.
A bounded agentic system that adapts network-transfer concurrency from live TCP telemetry while making every recommendation, constraint, and state transition inspectable.
Led an introductory competitive-programming workshop for more than 60 KUET students and helped organize programming contests.
Served as Assistant Organizing Secretary and helped run math events and Olympiad training.
Organized university sports activities and captained the CSE cricket team.