Machine Learning Engineer
Resume:
Yalda Amidi (Green Card Holder) *****.*****@*****.***
Boston, MA
Summary
Senior Machine Learning Engineer with expertise in applying machine learning and deep learning models, including Large Language Models (LLMs), to time series, healthcare and biotechnology data. Proven ability in Python programming, data science, and artificial intelligence. Over 6 years of research experience at Harvard Medical School
(postdoctoral fellow and research assistant), with a Ph.D. focused on signal processing, statistical methodology, and biomedical engineering
Technical Skills
• Programming: Python (TensorFlow, Pandas, Keras, Sklearn); MATLAB; C++; SQL
• Machine Learning Algorithms: SVM, KNN, Random Forest, Decision Trees, Gradient Boosting
• Large Language Models: Transformers, BERT, Large Language Models, Fine-Tuning LLMs
• Genomics & Data Analysis: Single-Cell Genomics, NGS Data Analysis, Data Engineering, Data Visualization
• Algorithms: Bayesian analysis, Expectation Maximization, Kalman Filters, Compressive Sensing, Convex Optimization
• Statistical Models: GLM, GMM, Maximum Likelihood Estimation, Bayesian Time-Series Classifiers, Hidden Markov Models
• Neural Networks: LSTM, CNN, Siamese Networks, Graph Neural Network
• Mathematics Tools: Wavelet Analysis, Time Series Analysis, Predictive Analytics Work Experience
Senior Machine Learning Engineer
Arbor Biotechnologies, Boston, MA 01/2024 – 10/2024
• Developed machine learning methods to rank and score mutagenesis candidates, reducing analysis time by 30%, and accelerating protein optimization workflows.
• Fine-tuned Large Language Models to enhance protein thermo-stability predictions, driving improved model accuracy by 23%.
• Led ML-powered experimental designs and data analyses to optimize nucleus functionality, cutting experimental iteration cycles by 31%.
• Developed computational methods and ML models to predict Cas12i2 editing outcomes with a 93% prediction accuracy using large pooled screening datasets. Postdoctoral Research Fellow
Harvard Medical School, MGH, Boston, MA 08/2021 - 01/2024
• Applied machine learning models to forecast neurotoxicity syndrome following CAR-T cell therapy with a 92% sensitivity and 88% specificity.
• Designed and trained a Siamese neural network to analyze and cluster over 60,000 EEG segments of real-world data, achieving 87% clustering accuracy.
• Developed deep learning algorithms to identify hidden consciousness in brain-injured patients, improving detection rates by 25%.
• Implemented Kalman Filters and Expectation Maximization to estimate parameters in physiological models, analyzing over 60,000 data points with 10% reduced error. Machine Learning Research Scientist (Internship)
Harvard Medical School, MGH, Boston, MA 12/2018 - 08/2021
• Clustered human movement data using hierarchical K-means for neurological applications.
• Developed a Poisson state-space model to estimate moment-to-moment speech intent during conversations.
• Created a Bayesian time-series classifier to design neural encoders/decoders in DARPA-funded cognitive state decoding projects.
Machine Learning Engineer
MISP (Medical Image and Signal Processing) 08/2012 - 09/2015
• Developed machine learning and statistical methods to classify clinical imaging patterns into healthy or diseased states.
• Designed semi-automatic algorithms for segmenting layers and objects in optical coherence tomography images.
Education
Ph.D., Electrical & Computer Engineering GPA: 4.0/4.0 Isfahan University of Technology, Iran 09/2015 - 03/2021
• Focus: Electrical Engineering, Biomedical Engineering
• Thesis: Developed computational models to estimate neural activity.
• Coursework: Advanced DSP, Convex Optimization, Linear Algebra, Geometry of Manifolds, Graph Theory M.Sc., Electrical & Computer Engineering GPA: 4.0/4.0 Yazd University, Iran 09/2010 - 08/2012
• Focus: Signal Processing, Data Science
• Thesis: Enhanced face verification systems using compressed sensing techniques.
• Coursework: Stochastic Processes, Computer Vision, Pattern Recognition, Machine Learning, DSP B.Sc., Electrical Engineering GPA: 3.8/4.0
University of Isfahan, Iran 09/2006 - 08/2010
• Thesis: Designed and implemented the Modbus protocol using AVR and C++. Selected Publications
Amidi, Yalda, et al. "Forecasting immune effector cell-associated neurotoxicity syndrome after chimeric antigen receptor t-cell therapy." Journal for Immunotherapy of Cancer 10.11 (2022).
Amidi, Yalda, et al. "Parameter estimation in multiple dynamic synaptic coupling model using Bayesian point process state-space modeling framework." Neural Computation 33.5 (2021): 1269-1299.
Yousefi, A., Amidi, Y., Nazari, B., & Eden, U. T. (2020). Assessing goodness-of-fit in marked point process models of neural population coding via time and rate rescaling. Neural computation, 32(11), 2145-2186.
Amidi, Yalda, et al. "Continuous prediction of cognitive state using a marked-point process modeling framework." 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society
(EMBC). IEEE, 2019.
Amidi, Yalda, et al. "Parameter estimation in synaptic coupling model using a point process modeling framework." 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
(EMBC). IEEE, 2018.
Contact this candidate