Andrew
DiCosmo

A live AI-enabled SaaS marketplace for collectors: computer vision recognition, OCR, live market pricing, and a social layer with leaderboards. I design and build its recognition and OCR workflows, cloud AI service integrations, backend data flows, API integrations, and production architecture. The approach favors bounded recognition, pricing, and workflow services so AI output is useful without turning every step into an open-ended agent loop. See how it works in the demo below.

A private Shopify repricing system: an LLM can recommend a price, while deterministic policy and validation code control every write. It is an example of applying AI in production with clear guardrails.

An in-development business-operations platform. The current work focuses on shared customer and hiring workflows, with AI-assisted matching, drafting, and planning. Broader modules are planned rather than represented as finished product capabilities. See the concept view below.

W-2 and C2C work supporting Citizens Bank, where I was brought in as the Azure security subject matter expert for the content engineering team. I owned the Azure security product workstream, led Azure-related security efforts, and helped the team adopt Azure Advanced Threat Protection, Office 365 Advanced Threat Protection, and the broader Microsoft security suite. I also took on QRadar work outside the original Azure scope, helping the team write Splunk detection rules as they moved off QRadar. From there, I built an early Detection as Code prototype for Splunk rules, using source control to show file diffs, who changed a rule and when, and to support disaster recovery or rule restoration. Later, I helped implement Microsoft Purview data flowing into Splunk.

Publicly discussable summary of a C2C subcontractor engagement supporting FDIC as the end customer: platform security across more than 60 Azure subscriptions. I develop Azure Policy controls against the agency's customized security benchmark, publish reusable PowerShell governance modules, and automated a compliance investigation that previously took about a business day to run in under a minute. The work also includes Splunk correlation searches and AI-governance policy as the agency adopts AI.

C2C subcontractor engagements supporting Fortive, HCSC, and Guidestone as end customers: deployed and configured Microsoft Defender for Endpoint and Defender for Identity, reducing attack surface across corporate environments. Led Azure ATP implementations for real time threat detection, integrated Splunk and QRadar with the Defender stack across hybrid environments, and built Defender policy and automated security responses across the three end clients.

As BlackSpoke's CTO of Cloud, migrated DOJ Justice Management Division datacenter workloads into Azure, then led an NGA team building the agency's data lake. ETL pipelines supported petabyte-scale geospatial data across 30+ sources, reducing manual processing by roughly 60%. I also designed API microservices and data workflows for imagery cataloging using Python, Node.js, Lambda, NiFi, OpenShift, Docker, Terraform, SQL, Oracle, and SQL Server Integration Services (SSIS), with secure-environment deployment practices.

At BlackSky Technology (NYSE: BKSY), worked on Spectra, an AI-enabled space-intelligence platform that fused satellite imagery with SAR, RF, GPS, and IoT sensor data for object, change, and anomaly detection and site monitoring. The work included PyTorch and TensorFlow detection models, a continued NGA AWS microservices contract, and an IARPA program. This site presents an illustrative, unclassified visualization rather than program materials.

A publicly discussable, high-level summary of the largest production AI application I have worked on: a multi-year modernization of an existing cleared mission application. I led two delivery teams rearchitecting services on AWS using Well-Architected principles and loosely coupled microservices behind APIs. My teams owned Python API services end to end; I later worked alongside Java backend services in the same environment. The program operated at petabyte scale, with data warehousing measured in billions of records and continuous structured and unstructured ingest supporting mission-focused AI/ML, computer-vision, and geospatial workflows.

IDG and Dimension Data recognized the cloud architecture work at HARMAN Connected Services, where I ran the cloud practice from the first whiteboard to delivery across multiple portfolios.

C2C subcontractor engagement supporting NIKE as the end customer. Built a five year technology roadmap for NIKE's corporate information security team covering application security, cloud platform security, encryption and certificate management, vulnerability management, and penetration testing, and integrated CloudWatch, Rapid7, and AlienVault across 40+ Azure and AWS subscriptions.

As ByteCubed's Principal Big Data Architect, led an engineering team building big data platform solutions at scale, with DHS among the customers served. Owned software architectures, coding standards, code reviews, and the technical direction that kept feature delivery on time.

Eleven years teaching nights while building days: Visual Basic, Java, C#, C++, and Ethical Hacking, plus a seat on the IT advisory board. Also served as an exam development Subject Matter Expert for CompTIA and Microsoft. Explaining systems is how you find out if you understand them.

My own shop: custom desktop, web, and mobile apps for small and medium businesses, SharePoint and ASP.NET builds, network design, and cloud work that was early for its time: refactoring client applications to run in AWS and Azure and standing up DevOps pipelines for them. The anchor engagement was running IT for a group of eight affiliated companies, migrating all 300 users off Lotus Notes onto hosted Exchange 2007, and replacing their aging Access/SQL ERP with a Java and Oracle system with handhelds, cutting real cost in a crisis economy.

Started at Tufts Grinding as a W-2 employee, moved from shop-floor operations into IT and software, and built VB.Net inventory tools on Windows Mobile 5.0 with SQLite and barcoded labels, RFID on the shipping floor, bash scripts for supply-and-demand processing, and VMware virtualization. Later, Tufts became a client, and I supported them through consulting work before helping transition IT back into internal operations.