Deepali Sharma
- Cosmic Muon Monitoring System: Built automated daily monitoring pipeline (cron-based) predicting solar activity and space weather across multiple detector locations
- Jefferson Lab RICH Detector Analysis: Processed terabytes of experimental data using HPC clusters; published results in leading peer-reviewed journal
- ML Classification Projects: Delivered multiclass classification models (Random Forest, XGBoost) and CNN-based image classification achieving high recall metrics
- PHENIX Experiment Data Analysis: Analyzed petabytes of heavy-ion collision data; published as primary author in leading physics journals
Deepali Sharma
Deepali transitioned from fundamental physics research to applied data science, leveraging 12+ years of expertise in analyzing massive datasets and building ML pipelines. She combines rigorous scientific methodology with modern ML/DL techniques to solve complex real-world problems in healthcare, finance, and sustainability.
Route to AI Engineer, Data Scientist, Machine Learning Engineer teams building high-throughput services in the candidate's core stack.
Where this candidate belongs
Large-scale data processing and analysis (terabytes to petabytes). Machine learning & deep learning model development (Scikit-learn, Keras, XGBoost, LSTM, CNN). Scientific computing and statistical analysis with rigorous methodology. Data pipeline architecture (Bash, Perl, C++, SQL) on HPC clusters.
Data Engineer, Data Scientist, Machine Learning Engineer, Analytics Engineer.
On-site. Based in Setauket, US.
Targeting $130K+. Currently: Research Scientist.
Recruiter screen → hiring-manager review → technical conversation around Cosmic Muon Monitoring System, Jefferson Lab RICH Detector Analysis, ML Classification Projects.
Deepali's work in Data Engineer, Data Scientist, Machine Learning Engineer translates directly into adjacent domains with similar architecture, scale, and reliability needs.
- Primary production depth is the candidate's core stack. Other tooling framed as ramp/adjacent unless proven.
- Leadership framing is technical leadership (mentorship, code review, architectural direction). Formal people-management should be validated per role.
- Additional interests are personal/research at present, not production claim.
Master Proof Matrix
This reusable proof index maps common senior/staff engineering requirements to candidate proof. Role-specific addenda extend — not replace — this base matrix.
Requirement: Deliver on cosmic muon monitoring system at production scale.
Proof: Built automated daily monitoring pipeline (cron-based) predicting solar activity and space weather across multiple detector locations
Requirement: Deliver on jefferson lab rich detector analysis at production scale.
Proof: Processed terabytes of experimental data using HPC clusters; published results in leading peer-reviewed journal
Requirement: Deliver on ml classification projects at production scale.
Proof: Delivered multiclass classification models (Random Forest, XGBoost) and CNN-based image classification achieving high recall metrics
Requirement: Deliver on phenix experiment data analysis at production scale.
Proof: Analyzed petabytes of heavy-ion collision data; published as primary author in leading physics journals
Requirement: Ship work that requires large-scale data processing and analysis (terabytes to petabytes).
Proof: Demonstrated at prior roles.
Requirement: Ship work that requires machine learning & deep learning model development (scikit-learn, keras, xgboost, lstm, cnn).
Proof: Demonstrated at prior roles.
Technical Proof Catalog
Built automated daily monitoring pipeline (cron-based) predicting solar activity and space weather across multiple detector locations
Processed terabytes of experimental data using HPC clusters; published results in leading peer-reviewed journal
Delivered multiclass classification models (Random Forest, XGBoost) and CNN-based image classification achieving high recall metrics
Analyzed petabytes of heavy-ion collision data; published as primary author in leading physics journals
Mid — role fit: adjacent.
Senior — role fit: primary.
Senior — role fit: primary.
Senior — role fit: secondary.
Visual Evidence Index
github.com/deepssharma — public repositories, contribution activity, and open source project surfaces.
https://pypes.dev/deepali-sharma
Hosted candidate portfolio with positioning, proof points, and conversion kit surface for recruiter routing.
www.linkedin.com/in/deepali-sharma-a83a126
Professional profile and recruiter connection path.
Contact Deepali Sharma
Route this candidate now.
This kit is designed to survive internal forwarding. The fastest next step is a recruiter screen, hiring-manager review, referral handoff, or direct call.
Primary fit: AI Engineer, Data Scientist, Machine Learning Engineer.
https://pypes.dev/deepali-sharma
Fastest way to reach Deepali — grab a slot on their calendar.
Persistent candidate surface for routing, resume, and proof surfaces.
Professional profile and recruiter connection path.
Public engineering surface, repositories, and OSS project path.
Additional candidate-owned portfolio and technical writing surface.
Deepali Sharma is a Setauket, US-based AI Engineer. Deepali transitioned from fundamental physics research to applied data science, leveraging 12+ years of expertise in analyzing massive datasets and building ML pipelines. She combines rigorous scientific methodology with modern ML/DL techniques to solve complex real-world problems in healthcare, finance, and sustainability. Best fit: AI Engineer, Data Scientist, Machine Learning Engineer.