Computer Science at NYU Abu Dhabi

Ashmit Mukherjee

Computer Science student at NYU Abu Dhabi | Computational Social Science | Applied Machine Learning | Experimental Research

I am a computer science student at New York University Abu Dhabi, graduating in May 2027.

My work spans computational social science, applied machine learning, and experimental research. I use statistical and computational methods to investigate social, economic, and historical questions. I also build the systems needed to collect data, run experiments, and evaluate models.

I currently lead the technical implementation of an online platform for a human-AI research project and contribute to study design. At the eBRAIN Lab, I build training and evaluation pipelines for adapting protein language models. I have also worked on multilingual natural language processing, applied data analysis, and software systems.

I am most interested in work that follows the full empirical cycle: formulating a question, structuring data, building a model or system, testing it, and interpreting what the evidence means.

Research

My research interests lie in computational social science, applied machine learning, and experimental research. I use statistical and computational methods to investigate social, economic, and historical phenomena. Depending on the question, the work may involve constructing data, designing an experiment, training a model, building a research platform, or evaluating whether an apparent result survives repeated testing.

Research areas

Computational social science

I am interested in the empirical study of institutions, markets, collective behavior, language, culture, and historical change. Computation is useful because it allows questions to be operationalized, measured, and examined across forms of data that would otherwise be difficult to analyze systematically.

Applied machine learning and AI evaluation

I train and adapt models, construct evaluation pipelines, compare meaningful baselines, and examine how results change across repeated runs and model configurations. I am especially interested in the difference between an apparent improvement and one that remains credible after controlled evaluation.

Experimental research and research engineering

I enjoy research in which the experimental system is itself a substantial part of the work. This includes translating theoretical questions into procedures, implementing the research platform, validating its behavior, and producing data that can support a defensible analysis.

Current research

Human-AI collaboration

Research Assistant, New York University Abu Dhabi

At New York University Abu Dhabi, I contribute to the study design of an experimental research project on human-AI collaboration and lead the technical implementation of its online research platform.

My work focuses on translating theoretical requirements into platform behavior, structured validation checks, and data workflows for subsequent empirical analysis.

Protein language models

Research Assistant, eBRAIN Lab, New York University Abu Dhabi

At the eBRAIN Lab, I develop and evaluate parameter-efficient methods for adapting protein language models to protein-sequence tasks.

The work focuses on constructing training and evaluation pipelines, running multi-seed experiment sweeps on the university high-performance computing cluster, and examining whether results remain stable across model configurations.

Previous research

Hinglish named-entity recognition

Fine-tuned mBERT and XLM-RoBERTa for named-entity recognition on Hindi-English code-mixed text from COMI-LINGUA and benchmarked them against zero-shot general-purpose language-model baselines.

Repository → Research report →

Projects

Selected projects in applied machine learning, data analysis, multilingual NLP, and software systems.

Data Science Salary Prediction Platform

  • Built an AutoML salary-prediction workflow using cleaned Glassdoor job-listing data, with PyCaret model comparison, XGBoost, SHAP interpretation, MLflow experiment tracking, and Streamlit.

Methods PyCaret, XGBoost, SHAP, MLflow, Streamlit

Repository →

Crime Data Analysis and Prediction Platform

  • Modeled observational relationships between socioeconomic indicators and violent-crime rates across U.S. communities using regression and holdout evaluation, with an interactive application for descriptive exploration and model-based prediction.

Methods scikit-learn, pandas, Plotly, Streamlit, regression

Repository →

Hinglish Named Entity Recognition Benchmark

  • Fine-tuned mBERT and XLM-RoBERTa for named-entity recognition on Hindi-English code-mixed text from COMI-LINGUA and benchmarked them against zero-shot general-purpose language-model baselines.

Methods PyTorch, Hugging Face Transformers, multilingual NLP, entity-level evaluation

Repository → Research report →

CAMP: Campus Asset Management Platform

  • Designed and implemented a multi-user resource scheduling platform with role-based access control, conflict-resolution workflows, authenticated REST APIs, and GitHub Actions CI/CD.

Methods React, Node.js, MongoDB, REST APIs, GitHub Actions

Repository →

Experience

Research Assistant, Human-AI Collaboration

New York University Abu Dhabi

  • Lead the technical implementation of an online platform for a human-AI research project.
  • Build, deploy, and maintain the system used to conduct the research and collect structured experimental data.
  • Contribute to study design and translate research requirements into platform behavior, data workflows, and validation checks.

Research Assistant, eBRAIN Lab

New York University Abu Dhabi

  • Develop and evaluate parameter-efficient methods for adapting protein language models to protein-sequence tasks.
  • Build training and evaluation pipelines and run multi-seed experiments on the NYU Abu Dhabi HPC cluster.
  • Compare models and configurations to determine which results hold up across repeated runs.

Machine Learning Engineer Intern

Zeek

  • Built and evaluated customer-segmentation workflows using real-world data.
  • Compared preprocessing and model choices, then used SHAP to inspect model behavior.
  • Contributed to validation and evaluation procedures used in the model-development workflow.

Market Research Consultant

Global Media Alliance Broadcasting

  • Led audience analysis, survey design, and customer engagement analysis for a broadcasting company.
  • Synthesized quantitative and qualitative findings into recommendations presented to senior leadership.

First Year Program Facilitator

Office of Student Life, New York University Abu Dhabi

  • Facilitated workshops, group discussions, peer activities, and weekly one-to-one check-ins for more than 20 first-year students.
  • Connected students with academic, wellbeing, and campus resources and organized off-campus cultural excursions.

Front of House Staff

New York University Abu Dhabi Arts Center

  • Managed guest check-in, crowd flow, and ticketing operations for events with more than 500 attendees.
  • Supported VIP guests, performing artists, and last-minute operational changes.

Education and technical skills

New York University Abu Dhabi

B.S. in Computer Science. Study away: NYU Paris and NYU New York.

Relevant coursework Natural Language Processing, Principles of Data Science, Statistics, Data Structures and Algorithms, Computer Systems Architecture, Operating Systems.

Pinned core skills

Python Machine Learning Experimental Design

Programming languages

Python C++ C# JavaScript

Machine learning & NLP

PyTorch Hugging Face Transformers scikit-learn XGBoost PyCaret SHAP LoRA ESM-2 Natural Language Processing

Data & statistics

Computational Social Science Data Analysis Statistical Analysis Model Evaluation Research Design pandas NumPy SciPy Matplotlib Seaborn Plotly

Systems & infrastructure

FastAPI Empirica REST APIs MongoDB Docker Slurm pytest MLflow GitHub Actions Git Streamlit LaTeX