Summer 2026 Technology Internship Program

Reduced data retrieval time by ~97% by developing a Python CLI tool leveraging the AVEVA PI Web API, replacing a manual Excel-based ingestion process with automated shell scripts for monthly analyses.

Engineered a real-time monitoring system for high-volatility data center loads, enabling predictive generation dispatch that reduced Area Control Error (ACE) swings and prevented frequency-based grid instability.

Established the organization's top-performing winter peak demand forecast by implementing an XGBoost model with tailored meteorological features and data center load-growth analysis, reducing MAPE by 47%.

Enabled identification of undiagnosed patients and risk flagging by building a BERT-based model that encoded longitudinal claims data into dense embeddings, supporting patient journey clustering across large populations.

Strengthened risk assessment for an anti-seizure medication by developing a survival analysis model with left-truncation and right-censoring corrections, benchmarking internal outcomes against real-world evidence.

Validated drug usage patterns for a rare pediatric epilepsy disorder by running subpopulation analyses across Snowflake, surfacing prescribing trends that informed commercial strategy.

Built an AI analytics team agent mapped to client business semantics, letting executives query metrics in natural language and auto-generate dashboards, accelerating decision-making and reducing analytics backlog.

Resolved errors in forecast bias and accuracy queries by curating a RAG-driven Text-to-SQL dataset of validated natural language-to-PostgreSQL pairs, increasing agent query accuracy by 16%.

Optimized large-scale competitor product matching by migrating sequential embedding workflows to OpenAI's Batch API, reducing costs by 50% and accelerating throughput for thousands of SKUs.