Shail K Patel

Founding ML Engineer at Stealth Startup, building intelligent systems from the ground up. Let's turn your product vision into working architecture.

Connect Resume

EXPERIENCE

Stealth Startup (Restaurant Tech)

Founding Machine Learning Engineer

Seattle, USA
Nov. 2025 – present
  • Architected the full technical stack from scratch based on CEO requirements, spanning ML pipelines, Django backend services, and complete database design.
  • Directed a small engineering team across the full stack, setting implementation standards and driving all key technical decisions.
  • Established the entire technical foundation with no prior codebase, designing all schemas and integration points for production-ready functionality.

GetMySpace (Parking Management Startup)

Machine Learning Engineer

Ahmedabad, India
Jan 2025 – Jun 2025
  • Built GetMySpace's first AI prototype for real-time parking management, integrating computer vision and ML to automate vehicle and slot detection end to end.
  • Reduced end-to-end processing to ~4s and real-time update latency to ~0.7s through optimized Python and PyTorch model deployment.
  • Implemented MongoDB-based backend to manage prediction outputs, user logs, and dynamic updates at scale.

PUBLICATIONS

A Two-Stage, Leakage-Aware Framework for Early Academic Risk Detection in Undergraduate Engineering Cohorts

Student Performance Prediction, Early Warning Systems, Ensemble Learning, Stacked Classification, Leakage Prevention, SHAP
  • Proposed and implemented a leakage-aware, two-stage ML framework to forecast student academic decline
  • Applied leakage-aware modeling to ensure predictions are temporally valid and unbiased
  • Evaluated 50+ regression pipelines per subject (≈200 total) to benchmark academic performance forecasting methods
  • Tested 50+ classification pipelines for risk detection; best-performing stacking ensemble achieved recall 0.657
  • Applied explainability (SHAP) to support model interpretability and trust
Paper: doi.org/10.5281/zenodo.19686376
1 / 1

PROJECTS

PredictGrad

predictgrad.streamlit.app
Ensemble Stacking · BayesSearchCV · Voting Regressor · SHAP/XAI · Boruta Feature Selection · Class Imbalance Handling
  • Built a full ML pipeline to predict future semester marks and detect academic risk
  • Regression: Voting Regressor (Ridge + Lasso + ElasticNet)
  • Classification: Stacking (CatBoost, LGBM, ExtraTrees)

Régions Inégales: Regional Firm-Creation Attribution Model

regions-inegales.streamlit.app
Python, XGBoost, SHAP, Pandas, Streamlit
  • Built a decade-long panel from six official French sources, harmonizing inconsistent schemas across all departments
  • XGBoost model with leave-one-department-out cross-validation, achieving R² = 0.674 on unseen departments
  • SHAP attribution showed opportunity features (60%) vastly outweighed necessity (15%), with unemployment ranking last

Beyond The Marks

beyondthemarks.streamlit.app
Python, SHAP, Pandas, Seaborn
  • ML pipeline with explainable AI to analyze student performance
  • Detects grading bias and assesses influence of sensitive attributes
  • Quantified teacher effectiveness with performance indicators

CERTIFICATES

SKILLS

AI & Agents

  • LangChain
  • LangGraph
  • n8n
  • LlamaIndex
  • Hugging Face
  • OpenAI API
  • Prompt Engineering
  • RAG Pipelines

Backend & APIs

  • FastAPI
  • Django
  • Flask
  • Streamlit
  • REST API
  • Python

Data & Tools

  • PostgreSQL
  • MongoDB
  • MySQL
  • Docker
  • Git
  • Postman
  • System Design
  • Linux
  • LiteLLM

Product & Strategy

  • Product Thinking
  • User Research
  • Roadmapping
  • A/B Testing
  • Agile / Scrum
Get in touch

Let's Work
Together

I'm always excited to build systems that actually matter. If you have a product vision that needs intelligent architecture, or a technical challenge that needs ownership from first principles, let's talk.

Email Me shailpatel.connect@gmail.com
↗
LinkedIn shailkpatel
↗
GitHub shailkpatel
↗