Dhairya Shah

About

ML-focused builder who has shipped an end-to-end income-class prediction product: built the data pipeline, trained models, deployed via Streamlit with a live UI, and tracked success via accuracy (84%), adoption, and latency. Demonstrates strong practical MLOps instincts (Docker/Streamlit Cloud, logging/monitoring, caching) and data engineering reliability patterns (schema checks, idempotency, retries, backfills) while iterating quickly in ambiguous, solo-project environments.

Experience

Education

Key Strengths

• Owned end-to-end ML product feature (data pipeline, model training, deployment, UI)
• Measured and improved model performance (reported 84% accuracy) and user adoption
• Inference latency reduction via vectorization, preloading models, batching, and removing redundant transformations
• Built and operated deployments using Streamlit Cloud and Docker with logging, caching, and latency monitoring
• High-ownership MVP delivery under ambiguous requirements; rapid iteration based on feedback
• Designed maintainable modular architecture (separating data/business logic/UI) enabling easier model swaps and fewer regressions
• Reliable ETL design with schema checks, idempotency, retries, rerunnable backfills, and anomaly detection
• OS-level concurrency and synchronization (semaphores) to remove busy-waiting
• Understanding of process scheduling and priority issues (e.g., priority inversion)
• Foundational knowledge of ML/DL and reinforcement learning concepts
• Hands-on experience using Docker in academic projects
• Basic understanding of Kubernetes for distributed environments