Vetted AWS Professionals

“Built and productionized a dual-agent LLM invoice-processing system for GFI Partners, adding guardrails and audit trails to earn stakeholder trust and drive adoption while cutting operational burden by 75%. Uses LangSmith observability to diagnose real-time workflow regressions and has experience teaching agentic AI concepts (e.g., at Carnegie Mellon) through hands-on, scaffolded demos.”

“Backend/data engineer with production experience at Walmart and HealthSnap building Python services and data pipelines on AWS (EKS, Lambda, Glue, Airflow). Strong reliability and operations focus—implemented idempotency + circuit breakers for peak-traffic consistency issues, GitOps CI/CD, and observability. Demonstrated measurable performance wins (Postgres p95 45s to <5s, ~60% CPU reduction) and modernized SAS batch workflows to Python with parallel-run parity validation and feature-flagged rollout.”

“Full-stack, design-minded developer who builds interactive, motion-forward experiences and translates complex creative coding (Three.js/p5.js/GLSL) into accessible UI for non-technical clients. Delivered an end-to-end manufacturing quality control image system for ChargePoint (React dashboard + AWS) and has hands-on field research experience from Hyundai EV user interviews; currently leading development of a virtual gallery for Creative Coding NYC.”

“Built and shipped a production LLM-driven multi-agent platform (ciATHENA) at CustomerInsights.AI to automate analytics/ML/compliance workflows in healthcare and life sciences. Implemented LangGraph/LangChain orchestration with strong backend-style rigor (schemas, Pydantic validation, retries, auditability) and optimized latency/cost while keeping the system usable for non-technical users via guided natural-language interactions and structured/visual outputs.”

“Backend/data engineer who has owned production Python APIs and high-throughput async workflows on AWS (FastAPI, Docker, ECS/EKS/Lambda) with mature reliability practices like idempotency, bounded retries, circuit breakers, and strong observability. Also built AWS Glue ETL into an S3/Redshift lakehouse and modernized legacy batch systems via parallel-run parity testing and feature-flagged migrations, including a SQL tuning win cutting a multi-minute query to under 10 seconds.”

“Former Xendit (YC-backed fintech) operator applying outcome-driven, scalable product-building experience to a new startup: a real-time, personalized real estate investment intelligence platform. Has begun prototyping, completed ROI analysis, and validated the space with US market research plus broker interviews in Chicago and Los Angeles, aiming to differentiate from Zillow/Redfin with goal-based ranked investment recommendations.”

“Full-stack engineer (Snowflake) who shipped an AI/LLM-powered data exploration product end-to-end, spanning Spring Boot/Python services and a polished React UI with streaming responses and robust fallbacks. Experienced operating high-scale AWS deployments (Docker/Kubernetes, SNS/SQS, RDS Postgres, CloudWatch, Jenkins CI/CD) supporting thousands to tens of thousands of concurrent users, including handling real traffic-spike scaling incidents.”

“ML/LLM engineer with production experience building a multi-GPU LLM inference platform using TensorRT and vLLM, achieving ~40% p95 latency reduction through batching/KV caching, quantization, and CUDA/runtime tuning. Also has end-to-end orchestration experience (Kubernetes, Airflow) and has delivered real-time fraud detection systems at Accenture in close collaboration with non-technical risk and product stakeholders.”

“Former multi-startup CTO with experience supporting successful capital raises and working directly with boards/investors. Known for implementing operational systems that reduce client escalations (e.g., a status/semaphore overview board) and for building UX-forward MVPs that evolve into automated platforms, including a loan underwriting system for a small US lender.”

“Built a production RAG-based "knowledge copilot" for support/ops using LangChain/LangGraph, implementing the full pipeline (ingestion, chunking, embeddings, vector DB retrieval/rerank, guarded generation with citations) and operating it as monitored microservices with CI/CD. Also designed an event-driven, streaming backend for real-time inventory ordering predictions that reduced stockouts by 25%, and has hands-on incident response experience stabilizing LLM API latency/5xx spikes using Datadog/APM and resilience patterns.”