Donald C.

Key Skills

Software

No software listed

Top Subject Matter

Chemical and materials science (reaction yield prediction)

Pharmaceutical analytical chemistry (HPLC/MS data acquisition)

Chemistry education and assessment

Top Data Types

Computer Code Programming

Top Task Types

Fine-tuning

Data Collection

Freelancer Overview

Research Assistant, Computational simulations and ML model development using reaction and spectroscopy data. Brings 7+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Python, N, and A. Education includes Bachelor of Science, Massachusetts Institute of Technology (MIT) (2018) and Certification, University of Chicago Booth School of Business (2024). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Fine-tuning, Data Collection, and Evaluation.

Labeling Experience

Research Assistant, Computational simulations and ML model development using reaction and spectroscopy data

Fine-tuning

In this role, you supported machine learning development by preparing and using historic chemical-reaction data to build a model for predicting reaction yields. You also applied spectroscopic measurements to product study work that would translate into structured inputs/outputs for downstream modeling. The work involved coding-driven data preparation and model-oriented evaluation to support reliable predictive outcomes. • Used Gaussian and Python to run computational simulations that generate model-ready numeric data • Built or contributed to a machine learning model predicting reaction yields from prior records • Optimized reaction conditions based on measured NMR/IR findings to improve yield • Produced research outputs (reports/publication) from analyzed datasets for model and scientific validation

2023 - Present

Analytical chemistry intern supporting experimental data preparation and statistical analysis

Data Collection

During this internship, you supported the acquisition and preparation of analytical chemistry datasets using HPLC and mass spectrometry outputs. You contributed to ensuring accurate data capture through equipment calibration and then performed statistical analysis on the resulting experimental data with Python. This enabled downstream interpretation and potential feature preparation for analytics or modeling. • Collected chromatographic and mass spectrometry measurements for pharmaceutical compound study • Optimized chromatographic conditions to reduce analysis time by 20% • Calibrated and maintained instruments to improve data accuracy and consistency • Performed statistical interpretation of experimental results using Python

2023 - 2023

General Chemistry Teaching Assistant (assessment/feedback on student outputs)

As a general chemistry teaching assistant, you evaluated student work through grading of assignments, lab reports, and examinations and enforced academic integrity and safety requirements. Your instructional guidance and feedback activities effectively supported structured assessment data useful for learning analytics. While not labeled as AI training, the responsibilities included repeated creation and review of labeled educational outputs. • Ensured submission, grading, and academic integrity for lab reports and exams • Guided group tasks to reinforce theoretical chemistry concepts • Provided individual instruction on experimental methods for large student cohorts • Managed safety observance in laboratory instruction settings

2020 - 2022

Artificial Intelligence-aided Chemical Data Analysis in Molecular Property Prediction

Fine-tuning

In this project, you trained an AI/ML model to predict molecular boiling points from chemical descriptors using supervised learning. You prepared or used a dataset of over 1,000 compounds and trained a TensorFlow model to achieve a strong predictive performance measured by R-squared. The outputs support model evaluation and potential iteration for improved predictive accuracy. • Trained a TensorFlow machine learning model using molecular descriptors as inputs • Used a dataset of more than 1,000 organic molecules for supervised training • Reported predictive performance with an R-squared of 0.92 • Presented findings at a chemistry symposium to obtain feedback for further iteration

Not specified

Education

Work History