AI Products. Shipped.

Production AI systems for markets, sports, and the enterprise. Three divisions, two operators, one company. Led by Robert D. Scott II (CEO) and Mark Conway (Director of AI).

Recent and prior engagements

01 / Engineering

AI Engineering

End-to-end AI system design — architecture, model selection, production hardening, and cost modeling. The engineering practice that ties everything below together.

Tools: Bedrock · Vertex AI · Azure AI

02 / RAG

RAG systems

From document ingestion through vector stores (OpenSearch, pgvector, FAISS) to retrieval-augmented chat with history and citations.

Tools: OpenSearch · pgvector · FAISS

03 / Agents

Agentic applications

LangGraph orchestration, tool use, multi-step reasoning, evaluation harnesses with Patronus AI or custom judges.

Tools: LangGraph · Patronus · Bedrock

04 / Multimodal

Multimodal pipelines

OpenAI vision, image-to-structured-annotation flows, hybrid image and text search.

Tools: OpenAI Vision · Hybrid retrieval

05 / Platform

LLM platform work

PortKey gateways, LangFuse observability, model routing across Bedrock, OpenAI, Anthropic, and OSS.

Tools: PortKey · LangFuse

06 / Classical

Classical ML

Recommender systems, demand forecasting, record linkage, semantic search with learning-to-rank.

Tools: XGBoost · Nixtla · AutoML

Spencer Gifts

Visual AI for in-store compliance

Visual AI models that measure in-store compliance across the chain — store openings, pylon placement, end-of-season resets. Adjacent work in Databricks: GenAI for costume fitting, plus ML sales and shipment forecasting.

Tools: Databricks · OpenAI Vision · Postgres

Datassential

Four Generative AI Products. Shipped.

Advised the C-suite on AI strategy and shipped four products over the engagement: Report Pro, Consumer Preferences, Menu Trends, and a chatbot. Built a Bedrock Agent pipeline that turned thousands of PowerPoint, PDF, and Excel reports into a searchable Knowledge Base — OpenSearch vectors, Foundation Models for parsing, Claude and GPT-4 for generation. Added hybrid image-and-text search via OpenAI vision, and engineered an agentic React + TypeScript chat with LangGraph orchestration and LangFuse observability.

Tools: Bedrock · OpenSearch · Claude · GPT-4 · LangGraph · LangFuse

LymeLess

Scalable agentic healthcare system on GCP

Designed a scalable agentic healthcare system on GCP with LangChain and LangGraph. Deployed with GitHub Actions and Workflows. Load-tested with Kubernetes and Locust, then tuned Firestore throughput under peak traffic.

Tools: GCP · LangGraph · GitHub Actions · Kubernetes · Firestore

Grindr

RAG pipeline for a consumer GenAI chatbot

Sentence-transformer embeddings, Postgres pgvector on AWS RDS, LangChain chat with conversation memory. Custom Patronus AI evaluators graded competing LLMs in a GitHub Actions regression suite. Kotlin microservices on EKS with Helm, Argo, PortKey AI gateway.

Tools: pgvector · LangChain · Patronus · PortKey · EKS

Ahold Delhaize

27% recommendation lift at 3 ms inference latency

Semantic search on T5 + SentenceTransformers + FAISS, with XGBoost learning-to-rank. Neural Collaborative Filtering on Azure Databricks scaled 20× via Petastorm and TorchDistributor. Hourly demand forecast across 2,000 stores on Nixtla.

Tools: T5 · FAISS · XGBoost · Databricks · Nixtla

Deloitte

Recommenders that funded a multi-year program

Built AzureML personalization and recommender models for an AI-driven shopping platform. The architecture blueprint was instrumental in securing several years of project funding. Implemented affinity and behavioral scoring on Azure Databricks using synthetic data, calculating Shapley values for visual feature-importance explanations. Wrote extensive model-validation Jupyter notebooks for the ensembles.

Tools: AzureML · Databricks · Shapley · Jupyter

Fidelity Information Services

Record linkage that unlocked $75M in contracts

Created synthetic, anonymized datasets from merchant transactions — work that spurred $75M in potential contract deals. Eliminated manual record matching with automated PySpark linkage over name, address, and merchant fields using tokenizers, N-grams, and Locality Sensitive Hashing. Generated demographic predictions with a Spark random forest classifier over consumer transactional features, extracting distribution features with vector assemblers, bucketizers, and custom UDFs.

Tools: PySpark · LSH · Random Forest · Synthetic Data

Fiat-Chrysler

$2.5M absence reduction across six auto plants

Led a small team that cut unplanned absences at six North American auto plants — saving $2.5M in employment costs using gradient boosting and time-series models over event and weather data. Built a Palantir Foundry pipeline that streamed vehicle sensor data (SQDF, Witech, Vstat, Data Logger), compressed it with Dynamic Time Warping, and chained LSTMs with Chi-Square analysis to predict warranty repairs. Presented a non-parametric Monte Carlo production-loss simulation to the CTO, contrasted against a parametric negative-binomial fit.

Tools: LSTM · Palantir Foundry · Gradient Boosting · Monte Carlo

Walmart / Sam's Club

A dozen ML models for Sam's Club on Hadoop

Led onshore and offshore teams to deliver over a dozen production models to Sam's Club on their Hadoop platform — demand forecasting, K-means customer segmentation, multinomial propensity scoring, churn/renewal/attrition (libsvm), basket analysis (R arules), X-13 ARIMA seasonality, and a dynamic-bidding offer-assignment algorithm. Ran extensive A/B experiments to measure uplift and statistical power on member campaigns. A greedy algorithm built in Apache Spark gave a 50× speedup on offer assignment.

Tools: Hadoop · Spark · libsvm · ARIMA

Project Workflow

01 / Scoping call

One hour, free

A written one-pager with proposed scope, milestones, and a fixed-fee or T&M option.

02 / Prototype

Two to four weeks

A working slice of the system, checked into your repo, running against your data.

03 / Hardening

Production handoff

CI/CD, evals, observability, cost controls, handoff docs.

04 / Optional retainer

Monthly block

Tuning, model updates, and incident response on a steady cadence.

Not a fit if

You need a 20-person agency, a pitch-deck consultant, or someone to tell you AI is the future. We're the engineers.

Tell us what you're building. We'll tell you whether we can help within a day.