Work

Production systems. Live. Measured.

AI and data infrastructure, in production at enterprise scale. Each system, what it solved, and the metric it moved.

5 systems

AI Engineering

Snowflake Cortex Multi-Agent Platform

Multi-agent LLM system over enterprise data. Semantic views deployed to enable natural-language querying across three business units, with full auditability and access controls. Outputs surfaced at VP level.

OutcomeVP-level adoption across 3 business units

Snowflake CortexMulti-AgentLLMSemantic Layer

AI Engineering

Most Recent

Real-Time NLP Sentiment + Market Intelligence

Production NLP pipeline combining customer sentiment analysis with competitive market intelligence. End-to-end: ingestion, transformer-based sentiment scoring, entity linking, and aggregated reporting.

OutcomeReporting turnaround cut from 2 weeks to 2 days (85% faster)

NLPStreamingPythonHuggingFace

MLOps

Most Recent

ML-Based Anomaly Detection on Snowflake

ML system continuously monitoring query execution patterns across thousands of daily runs. Surfaced model degradation, data integrity failures, and performance regressions before they reached downstream AI systems.

OutcomeCaught 12+ production-impacting regressions before user impact

MLOpsAnomaly DetectionTelemetryDrift Detection

Data Engineering

Recent

Real-Time Booking Trend Intelligence

Continuous monitoring of reservation signals — providing revenue operations with 24–48 hour early-warning capacity and informative diagnostic outputs for downstream decision workflows.

Outcome24–48 hour lead time on revenue decisions

StreamingTime SeriesSnowflake

Data Engineering

Recent

Airflow-Orchestrated Multi-Cloud ETL

Scalable Airflow (Astronomer) workflows across Snowflake, Azure, and ADLS — forming the validated, high-integrity data foundation that all four production AI systems depend on.

OutcomeReduced manual intervention by 70%, resource consumption by 30%

AirflowAstronomerSnowflakeADLS

Earlier roles available on request — see also the GitHub profile.