Fardin Ahsan Sakib

PhD Candidate, Computer Science
George Mason University

Graduate Research Assistant @ George Mason University AI Research Intern @ Comcast

I am a doctoral researcher in the Department of Computer Science at George Mason University and a member of the MasonNLP Research Group. My research spans the large language model lifecycle — interpretability, post-training, and evaluation — aimed at understanding how these models behave and making them dependable for real-world, high-stakes use such as clinical NLP and healthcare, with work published at venues like ACL and EMNLP. A central thread is AI safety: making models and the systems built on them fairer, more robust, and better aligned — from mitigating bias and reliability failures in LLMs to AI safety in multi-agent systems. Through research internships at Comcast, Fujitsu Research, and Amazon, I extend this to applied agentic AI — including agentic memory, agent evaluation, coding agents, and tool-calling workflows.

AI Safety Multi-Agent Systems Agentic Memory Agent Evaluation Large Language Models Post-Training Mechanistic Interpretability Clinical NLP
LinkedIn Google Scholar
Fardin Ahsan Sakib

Recent News

Experience

AI Research Intern

Comcast
June 2026 – Present
  • Researching agentic memory for large language model agents.

Agentic AI Research Intern

Fujitsu Research of America
November 2025 – January 2026 Santa Clara, CA
  • Trained a verifier model for coding agents that evaluates and selects the best solution from multiple agent attempts on real-world software engineering tasks (SWE-Bench), improving resolve rate by 15%.
  • Designed and implemented an end-to-end evaluation pipeline for scoring and ranking agent-generated solutions across multiple runs, supporting the team's research on inference-time scaling for coding agents.

Applied Research Scientist Intern

Amazon (AWS Support)
June 2025 – August 2025 Seattle, WA
  • Built CloudNEST, an expert-validated dataset for multi-step AWS tool calling (5–10+ chained APIs with cross-service dependencies) to assess agentic-AI workflows pre-production.
  • Developed AWSBench, a deterministic AWS response simulator and evaluation harness enabling credential-less, cost-free, reproducible benchmarking with standardized precision/recall scoring for API selection, parameter extraction, and step sequencing.
  • Benchmarked leading LLMs; identified failure modes (wrong API, name/parameter-format mismatches) and established baseline metrics (best 38% recall, 19% precision) for internal evaluations.

Applied Research Intern

Brillient Corporation
May 2024 – August 2024 Reston, VA
  • Developed key components of BRAG (Brillient Retrieval-Augmented Generation) using PyTorch, implementing query distillation and synonym generation modules to enhance contextual understanding across multiple domains.
  • Optimized information retrieval by designing efficient chunking algorithms and re-ranking methods, improving relevance by 22% (MAP) and reducing processing time by 35%.
  • Finetuned domain-specific LLMs and performed prompt engineering (chain-of-thought, tree-of-thought), deploying across medical, HR, and IRS domains with an 85% user satisfaction rate.

Graduate Teaching and Research Assistant

George Mason University
August 2021 – Present Fairfax, VA
  • Researching applications of Foundation Models to health data, focusing on social determinants of health for improved medical information retrieval and analysis.
  • Exploring methods to identify and mitigate bias in LLMs to improve fairness and accuracy in health-related AI systems, including explainability for transparency and trust.
  • Conducting labs and facilitating discussions for 100+ students; providing individualized feedback on assessments to improve engagement and understanding.

Machine Learning and AI Intern

Brillient Corporation
May 2023 – August 2023 Reston, VA
  • Engineered and fine-tuned NLP models for QA, summarization, emotion detection, and readability analysis, improving performance by 12–18% (F1, ROUGE, accuracy) for IRS and USCIS projects.
  • Built an end-to-end ML pipeline from model development to AWS deployment and API creation (SageMaker, Lambda, API Gateway), reducing deployment time by 40%.

Selected Publications

Trajectory-Guided Steering: Mitigating Spurious Feature Bias in Clinical Classification

Sakib, Fardin Ahsan; Ziwei Zhu; Özlem Uzuner
Under review at COLM 2026

Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models

Sakib, Fardin Ahsan; Ziwei Zhu; Karen Trister Grace; Meliha Yetişgen; Özlem Uzuner
ACL 2025
Paper

To token or not to token: A Comparative Study of Text Representations for Cross-Lingual Transfer

Rahman, Md Mushfiqur; Fardin Ahsan Sakib; Fahim Faisal; Antonios Anastasopoulos
MRL @ EMNLP 2023
Paper

Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti

Sakib, Fardin Ahsan; A. H. M. Rezaul Karim; Saadat Hasan Khan; Md Mushfiqur Rahman
BLP-2023 @ EMNLP 2023
Paper

MASON-NLP at eRisk 2023: Deep Learning-Based Detection of Depression Symptoms from Social Media Texts

Sakib, Fardin Ahsan; Ahnaf Atef Choudhury; Özlem Uzuner
CLEF 2023
Paper
View all publications on Google Scholar →

Awards & Honors

Distinguished Academic Achievement Award

George Mason University
2024

NSF Research Trainee (NRT) Fellowship

Center for Adaptive Systems of Brain-Body Interactions
2023

Academic Service

Reviewer — ACL Rolling Review (ARR)

Association for Computational Linguistics

Reviewer — Deep Learning for Code (DL4C)

Workshop @ NeurIPS

Reviewer — Bangla Language Processing (BLP)

Workshop co-located with EMNLP / IJCNLP-AACL

Technical Expertise

Research Areas

Large Language Models Foundation Models Generative AI Mechanistic Interpretability Inference-time Steering Post-training Bias Mitigation AI Safety Model Alignment Clinical NLP Healthcare AI

Methods

Fine-tuning LoRA RAG Verifier Models Reward Modeling Model Evaluation Benchmarking Agentic AI Coding Agents Multi-Agent Systems Tool Use Prompt Engineering Distillation

Frameworks & Tools

PyTorch Hugging Face Transformers Multi-GPU Training HPC Clusters Vector Databases Model Context Protocol (MCP)

Programming

Python C++ Java SQL

Cloud & MLOps

AWS (SageMaker, Lambda, API Gateway) Azure Docker Kubernetes Git

Education

Ph.D. in Computer Science

George Mason University
August 2021 – December 2026 Fairfax, VA · GPA 3.95 / 4.00

B.Sc. in Computer Science and Engineering

Islamic University of Technology
January 2017 – March 2021 Dhaka, Bangladesh · GPA 3.74 / 4.00

Press

George Mason University 08/2025 Article

AI's Blind Spots: One PhD Student's Clear Vision