Real-time AI video-creation engine:

‍
Built a multi-agent graph system that assembles MLS photos, clips, audio, and text into polished listing videos in < 5 s on GPU clusters, then auto-publishes to agents’ social channels.

Smart data ingestion pipeline:

‍
Developed an AI crawler that pulls images and metadata from agent sites, MLS, Zillow, and Redfin, cleans and deduplicates them, and unifies everything into a common schema for seamless editing.

Dynamic, brandable template system:

‍
Delivered an AI-driven template framework letting agents swap fonts, backdrops, marketing copy, and property details to produce highly personalized videos that match their brand style.

Scalable, secure multi-tenant platform & ops:

‍
Handles ~1 M listings with isolated databases for each brokerage, plus ongoing maintenance—already live with Sotheby’s agents.

‍

LLM-powered multi-agent AI health coach:

Built a personalized coaching system using LangGraph, orchestrating agents for fitness planning, nutrition, obstacle handling, and recipe recommendations. The system maintains evolving user profiles with both short- and long-term memory via vector embeddings.

Real-time insight extraction from voice calls:

Developed a Gemini LLM-based pipeline to transcribe human coach calls and extract actionable insights, enabling real-time updates to user plans.

AI-driven recipe engine with Instagram integration:

Developed a Gemini LLM-based pipeline to transcribe human coach calls and extract actionable insights, enabling real-time updates to user plans.

Enterprise-grade security and scalability:

Architected for millions of users with HIPAA and SOC-2 compliant infrastructure, integrated with leading EHR systems, and supported by dynamic prompt evaluation pipelines using LangSmith and Braintrust. Built with custom eval pipelines (LangSmith + Braintrust) to reduce hallucinations and ensure model quality through live and synthetic testing.

Multi-agent AI insights engine for financial data:

‍
Built ~10 interoperating graph-based AI agents that automatically ingest, categorize, and analyze transactions from all connected financial institutions, surfacing tailored insights such as spending trends, budgeting nudges, and savings opportunities.

AI-embeddings user memory for personalization:

‍
Developed a persistent vector-based memory system that captures financial behavior and user interactions, enabling agents to infer preferences, habits, and life context—powering deeply personalized financial advice.

AI-curated financial news feed:

‍
Delivered an embeddings-powered indexing and ranking engine that classifies trending news and matches it to individual users' financial interests and holdings—creating a personalized Bloomberg-like dashboard.

Scalable, secure, real-time infrastructure:

‍
Designed a high-throughput system with dynamic autoscaling, secure hybrid deployment (cloud + on-prem), and real-time inference—paired with ongoing operational support and regulatory-grade data protection.

‍

AI-powered site selection engine:

‍
Built a multi-dimensional regression tree model trained on US census, cellular, and ordering data to score millions of intersections and recommend optimal store locations—used by major retail and restaurant chains nationwide.

High-performance geospatial visualization:

‍
Delivered an SSE-based web map UI that streams server-rendered tiles and uses an AI model to reduce rendering load by intelligently narrowing the set of relevant intersections based on user input.

Dynamic, scalable modeling infrastructure:

‍
Engineered a concurrent data processing pipeline capable of re-running nationwide analyses in real time as users tweak parameters, handling massive datasets across geography, demographics, and sales history.

Auto-optimized multi-model framework:

‍
Built a model orchestration system using LLM-judging to auto-select the best fit across regression, random forest, and graph-based models—also supporting ensembling for more accurate recommendations.

‍

AI-powered cold-chain monitoring & alerts:

‍
Deployed a real-time IoT data pipeline that ingests terabytes of temperature, location, and handling events, then uses event-driven AI agents to flag anomalies and push instant alerts—helping prevent the $30 B annual loss of temperature-sensitive goods.

Adaptive temperature-control module:

‍
Designed an on-device AI algorithm that continuously tunes set-points in response to ambient conditions, removing the need for human intervention and ensuring medicines and vaccines stay within safe ranges in the field.

AI-generated compliance auditing:

Built a policy-based alert engine and automated, AI-driven audit report generator that produces secure, end-to-end traceability logs—dramatically cutting manual data-gathering time for regulatory reviews.

Secure, scalable IoT + mobile platform:

Implemented encrypted network tunnels, Bluetooth/Wi-Fi auto-reconnect mobile apps, and fault-tolerant cloud infrastructure to process tens of terabytes per day, with Plank providing ongoing maintenance and uptime assurance.

‍