Hello, I'm

Marian Dumitrascu

I build production GenAI systems on AWS — designed for the teams that own them.

Principal Cloud Solution Architect

AWS · Generative AI · Multi-Tenant SaaS

📍 Houston, TX20+ years experience

Technical Expertise

Comprehensive skills across AI/ML, Cloud Infrastructure, and Data Analytics

AI & Generative AI

Amazon Bedrock & Agentic AI

expert
BedrockClaude Sonnet 4Claude HaikuTitan V2 EmbeddingsAgentCore RuntimeStrands Agents SDK

RAG & Knowledge Bases

expert
Bedrock Knowledge BasespgvectorHybrid SearchRerankingEmbedding Pipelines

Multi-Agent Orchestration

expert
Coordinator + sub-agent patternsParallel and serial pipelinesTool callingStrands Agents SDK

Vision LLMs

expert
Bedrock Claude VisionOCRDocument extractionIndustrial Computer VisionMulti-color-space CV

Multi-Provider LLM Patterns

expert
Bedrock + OpenAI fallbackCost trackingMulti-level cachingGraceful degradation

AWS AI/ML Services

expert
SageMakerTensorFlowPyTorchScikit-learn

AI-Assisted Delivery

expert
Supervisor–Worker frameworkMulti-session AI orchestrationLiving-document state

Quantum Computing

advanced
IBM QiskitQuantum AlgorithmsQHack 2022
Cloud & Infrastructure

AWS Cloud Architecture

expert
AWS Certified Machine Learning Engineer – Associate (2025)

AWS Compute & Containers

expert
Lambda (Python and C++)SAMEC2ECSEKSFargate

AWS Data & Analytics

expert
RedshiftAthenaGlueEMR / SparkKinesisDMSStep FunctionsRDSAuroraDynamoDB

AWS Storage & Networking

expert
S3EFSFSxVPCIAMKMSCognitoCloudFrontELB

Multi-Tenant SaaS

expert
4-layer tenant isolation (session / proxy / service / database)Single-location, multi-location, franchise patterns

Stripe Billing Integration

expert
CheckoutCustomer PortalWebhooksConnectMetered billing

Infrastructure as Code

expert
TerraformCloudFormationAnsible

DevOps & Observability

expert
CloudWatchX-RayStep FunctionsCI/CD pipelines
Data, Engineering & Practice

Languages

expert
Python (FastAPI, asyncio, SQLAlchemy, Pydantic, Pytest)TypeScriptC++ (production AWS Lambda)JavaC#R

Web Development

expert
Next.js 15 / React 19Tailwindshadcn/uiNextAuth.js v5PrismaVite

Data Engineering

expert
Streaming analytics (Kafka, Kinesis)Batch ETL (Glue, EMR / Spark)Vector / semantic searchEmbedding pipelines

Data Science & ML

expert
Statistical modelingHypothesis testingPredictive analyticsCohort and churn analysisKnowledge graphs and ontology extraction

Databases

expert
PostgreSQL + pgvectorDynamoDBMongoDBRedisAuroraMySQLSQL Server

Engineering Practice

expert
Test-driven development (320+ test suites)HIPAA-aware designMulti-tenant data isolationAI-assisted delivery methodology

Featured Projects

Real-world solutions demonstrating expertise in AI/ML, cloud architecture, and data science

AI/ML
AI-Powered Health & Wellness Platform

Nutrition-assessment, recipes, meal-planning, grocery-list, and gamification platform for a health and wellness startup, integrated with the Z-Code Social Determinants of Health survey and a closed feedback loop driving personalized recommendations. HIPAA-aware design.

Amazon BedrockBedrock AgentCore RuntimeBedrock Knowledge BasesClaude Sonnet 4+6 more

Migrated AI services from direct Bedrock API calls to deployed AgentCore Runtime agents (Assessment, Grocery, Chat, Meal Plan plus dietary and safety validators). Centralized prompt-template management in Admin UI; backend retrieves and compiles templates with per-user context. Recipes & Meal Plans powered by Bedrock Knowledge Bases with healing-herbs retrieval. Six admin-panel modules plus CSV import/export and backup/restore with dry-run. 320+ tests passing across backend, frontend, mobile, and E2E suites.

completed
AI/ML
AI-Powered Underwater Leak Detection (Industrial CV)

POC for an industrial QA partner: automated detection of gas leaks during underwater pressure-testing of meters from an 8-camera rig generating 2.2 TB of 4K video across 794 files. Interactive dashboard with PASS/FAIL determinations, frame-level evidence viewer, AI reasoning per call, and CSV/Excel exports.

Amazon BedrockClaude Vision LLMPythonOpenCV+3 more

Strategic pivot from YOLO object detection to Bedrock Claude vision LLM cut POC timeline from 3–4 weeks to 4 days and initial cost from $5K+ in annotation labor to under $50 in API spend, while gaining natural-language explainability per detection. v5 bubble-classification breakthrough distinguishing condensation/brushing artifacts from true gas-leak indicators: 100% API success across 783 frames analyzed; zero severe false alarms; 79.8% correct false-positive detection on brushing activity. Multi-color-space CV pipeline narrowed search space from 6+ hours of footage to 12.3 minutes (94% reduction).

completed
AI/ML
AI-Powered Venue Discovery & Recommendation Platform

Production-ready platform for natural-language venue search, AI-driven recommendations, AI receipt processing, and Stripe metered commission billing. Delivered in a 2–3 week intensive sprint with 362 tests at 100% backend coverage; shipped 7 versions for incremental client feedback.

Amazon BedrockTitan V2 EmbeddingsOpenAIClaude Sonnet 4+6 more

Hybrid semantic + structured + full-text search using Titan V2 embeddings (1024-dim) in pgvector with HNSW indexing combined with PostgreSQL tsvector and per-user personalization signals; sub-500 ms p95 search latency. Dual-provider AI architecture (AWS Bedrock primary, OpenAI fallback) with per-call cost tracking, multi-level caching, and request deduplication; ~50–70% cost reduction vs single-provider baseline; 99.9% effective uptime. AI receipt OCR via Bedrock Claude Sonnet 4 vision API at 85%+ accuracy with fuzzy venue matching driving Stripe metered billing.

completed
AI/ML
Educational Video Marketplace for New Parents

Multi-sided learning marketplace with educator and consumer roles, AI-assisted course creation with Mux video processing, RAG-powered course search, and Stripe Connect educator payouts.

Amazon BedrockBedrock Knowledge BasesRAGMux+6 more

Bedrock Knowledge Bases + RAG over course content with reranking and SSE-streamed UI for live progress visibility. AI-assisted course-creation pipeline integrating Mux video webhooks with FastAPI orchestration; replaced originally-planned Step Functions design with simpler in-process orchestration. Architecture rewritten mid-project from server-actions to explicit FastAPI / Next.js separation with documented API contract; full E2E test surface with Playwright + Vitest + Pytest.

in-progress
Cloud Architecture
AWS Infrastructure Provisioning Platform for Media Workflows

Production C++ AWS Lambda backend (43 endpoints) plus React 19 / Vite frontend automating Terraform-driven AWS provisioning with real-time SSE monitoring and broadcast media-services integration for a media-services company.

AWS Lambda (C++)AWS Lambda (Python)TerraformFastAPI+3 more

Deliberate two-phase delivery: 4-week Python / FastAPI prototype to validate requirements (28 MSL tests + 17 integration tests), then 3-week C++ migration to meet client tech preference; achieved sub-50 ms response times (vs 100–150 ms in Python) and lower Lambda execution cost. 100% API compatibility, full test suite ported.

completed
AI/ML
Supervisor–Worker AI Development Framework (Open Source)

Open-source methodology and document templates for managing complex software projects with AI coding assistants — splitting strategic planning, task delegation, and execution across role-specific chat sessions, backed by living-document artifacts (CURRENT-STATUS.md, DELEGATION-TRACKER.md, THINKING-LOG.md, WORKER-PROMPTS/).

MethodologyLiving-document templatesMulti-session orchestrationAI-assisted development

Used in production across the wellness platform's 320+-test buildout, the educational marketplace's 12-session migration, and other engagements. Public repository plus an in-depth LinkedIn writeup. The working method behind every recent client engagement.

in-progress

GitHub Activity

ML Demo

Try this interactive sentiment analysis model. Enter any text and see how AI interprets emotional tone in real-time.

0/500 characters

Try these examples:

About Me

Principal Cloud Solution Architect with 20+ years across software architecture, AI/ML, and data science — focused for the last four years on shipping production-grade GenAI systems on AWS. Strength: turning ambiguous business problems into running architectures, from discovery and scoping through reference implementation and clean handoff. Deep current practice in agentic AI on Amazon Bedrock (Claude family, AgentCore Runtime, Strands Agents SDK, Knowledge Bases / RAG), multi-tenant SaaS platforms, and AI-assisted delivery methodology.

Get In Touch

Interested in collaborating, hiring for a Principal-level GenAI role, or just want to chat about an architecture problem? Send a message and I'll get back to you within a business day.

0/4000