Roles & Internships

Built core agent orchestration and A2UI integrations for AWS data-center teams to query live schedule/risk data via an internal AI assistant. Owned 36 packages; authored 225 CRs (188 shipped) across TS, Python, and AWS CDK. Estimated business savings $400 billion after global rollout.

• A2UI Integration (React, TS, Zod): Spearheaded agent-to-UI contract and widget spec adopted by partner team. Developed production POC with 21 component adapters and strict runtime contract with a fail-closed validator.
• Schedule Analysis Engine (Python, Bedrock, MCP): Built critical-path engine over Primavera P6 XER exports as a remote MCP server on Bedrock. Added HTTP transport, presigned URLs, hierarchical auth, and DynamoDB lock; fixed a 30s timeout via AWS ADOT runner.
• Data-Lake Query Service (Fargate, Athena, Redshift): Built read-only MCP service over live build data with policy router (Athena for serverless scaling; Redshift dormant via a reversible flag).
• Assistant Connector (TS, Lambda, DynamoDB): Managed integration across 3 transport generations (Custom→ACP→HTTP streaming) with atomic lock, 3s ack path, and fail-closed harness. Extracted standalone ACP package (73 unit tests, 17/17 smoke tests) fixing stateless prompts via bounded transcripts.
• Incident Analysis: Launched incident post-mortem MCP service. Resolved platform-wide SigV4 signing defect blocking all registered services, fixed an OTel bug in shared services, and improved upstream system instructions.
• Toolkit & Analytics: Built agent toolkit adopted by BI org. Integrated usage metrics into company AI adoption dashboard with batched uploads and cost-center attribution.
• Practice: Convened architecture reviews with senior/principal engineers; wrote 9-doc, ~135-page handoff package (22 diagrams, 13 deep-dives) to ensure long-term system survival.

Tech: TS, Python, AWS (CDK, Lambda, Fargate, DynamoDB, Athena, Redshift), Bedrock AgentCore, MCP, ACP, SigV4, OpenTelemetry/ADOT, React, Zod, Streamlit, Mermaid.

• Created an Agentic AI system with anti-hallucination guardrails, intent classification, task decomposition, orchestration caching, and a novel dynamic tool generation capability with caching that fetches from a curated vectorized knowledge base of AWS datacenter best practices and live AWS datacenter build data. This allows datacenter professionals to interact with an intelligent assistant for their daily tasks, reducing an estimated 40% of the time they spend on manual analysis. Built with Amazon Bedrock, Open Search Serverless, Strands, and MCP, with support for multimodal models like Claude, Nova Premier, and Command R+.
• Developed secure, serverless, ML-based predictive algorithms for project management schedule evaluation, risk identification, and delay prevention, utilizing Amazon Textract OCR, Lambda functions, DynamoDB, S3 bucket encryption, Simple Queue Service, Docker, IAM auth, Amazon Redshift, and API Gateway. Saved $75M+ in mitigation costs, per Amazon management estimates.
• Integrated with 10+ internal tools, creating a seamless user experience within the larger AWS ecosystem, by collaborating with global teams in APEC, AMER, and EMEA regions. Contributed to an internal tool with a user base of 18,000 users.