{
  "$schema": "https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json",
  "basics": {
    "name": "Ambrose Tuscano",
    "label": "Software Engineer: backend, cloud and distributed systems, agentic AI",
    "email": "ambrosetuscanojobs@gmail.com",
    "url": "https://tascano.github.io/",
    "summary": "Software Engineer II at Microsoft on Azure Resource Graph (12B+ Azure resources a day). Previously Sr. Generative AI Engineer at Nissan (a production four-agent system on AWS Bedrock AgentCore) and Software Engineer at Amazon Ads (APIs at over 1M TPS, high-throughput data pipelines). Core expertise: distributed systems design, high-throughput data pipelines, serverless architecture, API development and modeling, ML/AI integration, infrastructure and performance optimization, real-time event-driven systems, observability, multi-agent system design, and prompt engineering. Open to backend engineering, cloud engineering, distributed systems and platform engineering, data infrastructure, and AI/agentic systems engineering roles.",
    "location": {
      "city": "Redmond",
      "region": "WA",
      "countryCode": "US"
    },
    "profiles": [
      {
        "network": "LinkedIn",
        "username": "ambrosetuscano",
        "url": "https://www.linkedin.com/in/ambrosetuscano/"
      },
      {
        "network": "GitHub",
        "username": "Tascano",
        "url": "https://github.com/Tascano"
      },
      {
        "network": "X",
        "username": "ambrose_tuscano",
        "url": "https://x.com/ambrose_tuscano"
      }
    ]
  },
  "work": [
    {
      "name": "Microsoft",
      "position": "Software Engineer II, Azure Resource Graph",
      "location": "Redmond, WA",
      "startDate": "2026-04",
      "summary": "Azure Resource Graph saves 12B+ unique Azure resources every day, aiming for 20B+.",
      "highlights": [
        "Designed, tested and rolled out new graph-relationship rules for Azure's cloud resource inventory graph, from implementation through region-by-region production rollout; the primary rule matched ~128K–150K resource snapshots a day after promotion.",
        "Improved observability of a high-throughput relationship-processing pipeline: per-record metric dimensions, fixes across 7 telemetry signals in three microservices, and new operational dashboards.",
        "Contributed to a five-region compute scale-out that roughly doubled processing capacity with no additional cloud spend, and drove the buildout of the same stack in a new Azure region (Australia East)."
      ]
    },
    {
      "name": "Nissan Motor Corporation",
      "position": "Sr. Generative AI Engineer",
      "location": "Franklin, TN",
      "startDate": "2026-02",
      "endDate": "2026-04",
      "highlights": [
        "Designed and shipped Tell Me More, Nissan's first AI product for the dealership business: a production multi-agent chatbot integrated into the dealership appointment pipeline.",
        "Architected a four-agent system (Conversation, Rubric, Vehicle History, Dealership Internal) on AWS Bedrock AgentCore with persistent session memory.",
        "Owned business engagement with dealership stakeholders, plus the AWS infrastructure, chat backend and partner integrations."
      ]
    },
    {
      "name": "Amazon Ads",
      "position": "Software Engineer, Publisher Technology",
      "location": "Arlington, VA",
      "startDate": "2022-05",
      "endDate": "2026-02",
      "highlights": [
        "Designed and built a scalable Ad Labeling Service with 5x the throughput of the legacy system.",
        "Engineered a serverless data lake (DynamoDB exports to Apache Iceberg, AWS Glue, Athena) with a 30-minute data freshness SLA.",
        "Built an agent-based label validation framework using MCP, and a Slack-integrated Bedrock RAG chatbot over Amazon Kendra.",
        "Built Step Functions workflows for real-time ad evaluation at 5K+ TPS with sub-second latency.",
        "Built Ad Registration Service APIs under 15 ms at 1,000+ TPS, with an ElastiCache-based ingestion system.",
        "Supported the launch and A/B testing of the Ad Relevance API and infrastructure for Amazon Retail at over 1 million TPS.",
        "Root-caused and fixed a 10% request drop by optimizing infrastructure scaling policies; improved alarms, monitoring and CI/CD.",
        "Tripled BrandSafety pipeline throughput (17M to 52M products a day), cutting a critical backfill from 45 days to under 14.",
        "Transitioned a service with six interdependent subsystems to a new team with 100% uptime."
      ]
    },
    {
      "name": "Openprise",
      "position": "Software Engineer",
      "startDate": "2022-02",
      "endDate": "2022-03",
      "highlights": [
        "Python integrations with the Google Calendar API and ETL into PostgreSQL."
      ]
    },
    {
      "name": "NXP Semiconductors",
      "position": "Software Engineering Intern, ML",
      "location": "San Jose, CA",
      "startDate": "2021-05",
      "endDate": "2021-08",
      "highlights": [
        "Revamped an ML test suite in Python and Keras, cutting runtime by 30% and manual intervention by 60%."
      ]
    },
    {
      "name": "University of Maryland, Baltimore County",
      "position": "Graduate Teaching and Research Assistant",
      "location": "Baltimore, MD",
      "startDate": "2020-08",
      "endDate": "2021-12",
      "highlights": [
        "Fine-tuned BERT models for multimodal fake-news classification; mentored students in Information Retrieval, Computer Security, Discrete Structures and Numerical Computations."
      ]
    }
  ],
  "education": [
    {
      "institution": "University of Maryland, Baltimore County",
      "area": "Computer Science",
      "studyType": "Master of Science",
      "startDate": "2020-01",
      "endDate": "2021-12"
    },
    {
      "institution": "University of Mumbai",
      "area": "Computer Science",
      "studyType": "Bachelor of Engineering",
      "startDate": "2015-05",
      "endDate": "2019-05"
    }
  ],
  "skills": [
    {
      "name": "Core expertise",
      "keywords": [
        "Distributed systems design",
        "High-throughput data pipelines",
        "Serverless architecture",
        "API development and modeling",
        "ML/AI integration",
        "Infrastructure and performance optimization",
        "Real-time event-driven systems",
        "Observability",
        "Multi-agent system design",
        "Prompt engineering"
      ]
    },
    {
      "name": "Languages",
      "keywords": [
        "Java",
        "Python",
        "SQL",
        "TypeScript",
        "JavaScript"
      ]
    },
    {
      "name": "Azure",
      "keywords": [
        "Azure Resource Graph",
        "Azure Resource Manager",
        "Azure Resource Notifications",
        "Service Fabric",
        "VM Scale Sets",
        "Azure Functions",
        "Event Grid",
        "Event Hubs",
        "Cosmos DB",
        "Azure Managed Redis",
        "Azure Storage",
        "Azure Data Explorer (Kusto)",
        "KQL",
        "Azure Monitor",
        "Azure DevOps"
      ]
    },
    {
      "name": "AWS",
      "keywords": [
        "Lambda",
        "Step Functions",
        "ECS",
        "Fargate",
        "EC2",
        "API Gateway",
        "DynamoDB",
        "RDS",
        "S3",
        "SNS",
        "SQS",
        "Kinesis Firehose",
        "Amazon MSK (Kafka)",
        "Glue",
        "Athena",
        "Redshift",
        "ElastiCache",
        "CloudWatch",
        "CloudFormation",
        "Bedrock",
        "Bedrock AgentCore",
        "SageMaker",
        "Kendra"
      ]
    },
    {
      "name": "Data",
      "keywords": [
        "Apache Iceberg",
        "PostgreSQL",
        "MySQL",
        "MongoDB",
        "Redis",
        "Memcached"
      ]
    },
    {
      "name": "Frameworks",
      "keywords": [
        "Spring Boot",
        "Guice",
        "Dagger",
        "Vert.x",
        "GraphQL",
        "Hibernate",
        "FastAPI",
        "Flask",
        "Django",
        "React",
        "TensorFlow",
        "Keras"
      ]
    },
    {
      "name": "AI",
      "keywords": [
        "Multi-agent systems",
        "MCP (FastMCP)",
        "LangChain",
        "LangGraph",
        "AutoGen",
        "Strands",
        "RAG",
        "Prompt engineering",
        "Claude Code",
        "GitHub Copilot"
      ]
    }
  ],
  "projects": [
    {
      "name": "Tell Me More: agentic car-diagnostic chatbot",
      "description": "Nissan's first AI product for dealerships: a production four-agent intake system on AWS Bedrock AgentCore.",
      "url": "https://tascano.github.io/notes/agents-service-bay.html",
      "keywords": [
        "AWS Bedrock AgentCore",
        "Strands",
        "Multi-agent systems",
        "FastAPI",
        "Python"
      ]
    },
    {
      "name": "Multimodal AI system for ad similarity detection",
      "description": "Transcribe, Rekognition and Bedrock turn ads into text embeddings in OpenSearch for k-NN and pairwise duplicate detection.",
      "keywords": [
        "AWS Bedrock",
        "LangChain",
        "OpenSearch"
      ]
    },
    {
      "name": "Enterprise GenAI knowledge and search platform",
      "description": "RAG over Amazon Kendra with Bedrock, MCP servers (FastMCP) for enterprise data sources, and multi-agent orchestration.",
      "keywords": [
        "MCP",
        "FastMCP",
        "LangChain",
        "LangGraph",
        "AutoGen",
        "AWS Bedrock",
        "Kendra"
      ]
    },
    {
      "name": "Peer-to-peer distributed file system",
      "description": "Python sockets and multi-threading with replication and versioning, plus a write-up on scaling it from one laptop to the internet.",
      "url": "https://tascano.github.io/notes/file-that-wouldnt-die.html",
      "keywords": [
        "Python",
        "Sockets",
        "Multi-threading",
        "Distributed systems"
      ]
    }
  ],
  "meta": {
    "canonical": "https://tascano.github.io/resume.json",
    "version": "v1.0.0",
    "lastModified": "2026-11-01",
    "pdf": "https://tascano.github.io/assets/Ambrose_Tuscano_Resume.pdf"
  }
}