Principal-level GenAI and ML engineering for teams that need the real thing — Bedrock agents, RAG pipelines, LangGraph orchestration, evaluation harnesses, observability.
What we build
End-to-end AI system design — architecture, model selection, production hardening, and cost modeling. The engineering practice that ties everything below together.
Bedrock · Vertex AI · Azure AI
From document ingestion through vector stores (OpenSearch, pgvector, FAISS) to retrieval-augmented chat with history and citations.
OpenSearch · pgvector · FAISS
LangGraph orchestration, tool use, multi-step reasoning, evaluation harnesses with Patronus AI or custom judges.
LangGraph · Patronus · Bedrock
OpenAI vision, image-to-structured-annotation flows, hybrid image and text search.
OpenAI Vision · Hybrid retrieval
PortKey gateways, LangFuse observability, model routing across Bedrock, OpenAI, Anthropic, and OSS.
PortKey · LangFuse
Recommender systems, demand forecasting, record linkage, semantic search with learning-to-rank.
XGBoost · Nixtla · AutoML
Recent engagements
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 GenAI and ML projects in Databricks.
Databricks · OpenAI Vision · Postgres
End-to-end Bedrock Agent over a multi-thousand document Knowledge Base
PowerPoint, PDF, and Excel reports turned into a searchable Knowledge Base. OpenSearch vectors, Claude and GPT-4 generation, OpenAI vision for image-content extraction. React + TypeScript chat with LangGraph orchestration and LangFuse tracing.
Bedrock · OpenSearch · LangGraph · LangFuse · Claude · GPT-4
Scalable agentic healthcare system on GCP
Designed a scalable agentic healthcare system on GCP with LangChain and LangGraph. Secured API surfaces via Azure Foundry. Load-tested with Kubernetes and Locust, then tuned Firestore throughput under peak traffic.
GCP · LangGraph · Azure Foundry · Kubernetes · Firestore
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.
pgvector · LangChain · Patronus · PortKey · EKS
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.
T5 · FAISS · XGBoost · Databricks · Nixtla
AzureML personalization blueprint for a shopping platform
Personalization architecture and an AzureML pipeline blueprint for a shopping platform.
AzureML · Personalization
Synthetic-data contracts and PySpark record linkage
Synthetic-data contracts and PySpark-based record linkage across large-scale financial data.
PySpark · Record Linkage · Synthetic Data
Absence forecasting with LSTM on Palantir Foundry
LSTM-based absence forecasting on Palantir Foundry.
LSTM · Palantir Foundry
Enterprise ML at scale
Production data science across Walmart and Sam's Club at enterprise scale.
Hadoop · Spark
How an engagement works
A written one-pager with proposed scope, milestones, and a fixed-fee or T&M option.
A working slice of the system, checked into your repo, running against your data.
CI/CD, evals, observability, cost controls, handoff docs.
Tuning, model updates, and incident response on a steady cadence.
Not a fit if
Tell us what you're building. We'll tell you whether we can help within a day.
