Vetted AWS IAM Professionals

“At KPMG, built and productionized a secure RAG-based LLM assistant that lets business and risk stakeholders query data warehouses in natural language, reducing dependence on data engineers for ad-hoc analysis. Demonstrates strong production rigor (Airflow orchestration, CI/CD, containerization), retrieval/embedding tuning (rechunking, semantic abstraction for structured data), and reliability controls (confidence thresholds, refusal behavior, monitoring and canary evals).”

“Full-stack engineer with hands-on experience building a large-scale healthcare claims and provider-enrollment system end-to-end (React frontend, Spring Boot microservices, PostgreSQL on AWS). Optimized high-volume claims processing (millions of records/day) using indexing/pagination and asynchronous workloads via AWS Lambda/Kafka, and deployed containerized services with Docker/Jenkins on AWS.”

“Backend engineer who built Flask-based microservices for a high-throughput risk engine, using Kafka for streaming decoupling and Redis for low-latency caching, with PostgreSQL + Cassandra for mixed relational and time-series needs. Has hands-on experience productionizing ML inference (Azure OpenAI/TensorFlow) behind REST APIs with async queues, batching, and caching, plus multi-tenant isolation via schema separation and RBAC with per-tenant rate limiting.”

“Backend/platform engineer who led an end-to-end Python (FastAPI) transaction analytics microservice for real-time financial monitoring, including SQS ingestion, scoring/aggregation, and low-latency APIs. Strong AWS + Kubernetes/GitOps background (EKS, ArgoCD, Jenkins, ECS/ECR, CloudWatch) with hands-on experience scaling event-driven systems and executing phased on-prem to AWS migrations.”

“Built and shipped a production Chrome extension (Promptly) that lets users select text on any webpage and transform it in place (rewrite/shorten/translate) using on-device AI plus external LLMs. Implemented a custom lightweight orchestration layer for prompt chaining, context flow, and output validation, and tackled tricky browser Selection API issues to preserve formatting while keeping the UX simple and fast.”

“Built a production "sentinel insight engine" to tame information overload from millions of product reviews and support transcripts, combining Azure OpenAI (GPT-3.5) zero-shot classification with a fine-tuned T5 summarizer to generate weekly actionable product insights. Demonstrated strong MLOps/production engineering by adding drift monitoring with embedding-based detection, integrating REST with legacy SOAP/queue-based CRM via FastAPI middleware, and scaling reliably on Kubernetes with HPA.”

“Cloud/Kubernetes-focused production engineer with experience running 99.95% uptime platforms across AWS/Azure/GCP. Strong in incident response and performance troubleshooting (including a 30% MTTR reduction), and in building secure CI/CD and Terraform-based IaC for AKS/GKE microservices with robust change controls and rollback practices. Notably does not have direct IBM Power/AIX/VIOS/HMC or PowerHA/HACMP ownership.”

“Backend-leaning product engineer with DevSecOps depth who has shipped real-time, Kafka-driven data pipelines and AI-enabled customer-facing features to production on AWS. Built a Spring Boot API layer serving real-time predictions at 100K+ requests/day, improving latency by 35% and user task completion by ~25%, and delivered a React/TypeScript dashboard plus a Postgres audit/history model optimized for search and large event volumes.”

“Senior software engineer with Amazon experience who owned end-to-end improvements to a real-time payment authorization service, rebuilding it as a reactive Spring WebFlux microservice with saga orchestration and Kafka event streaming, deployed on AWS EKS with strong observability. Also built React+TypeScript and Node/Express full-stack workflow apps (onboarding, campaign management, admin review) and has experience shipping quickly in ambiguous startup environments while maintaining reliability and data correctness.”

“Data engineer with end-to-end ownership of large-scale retail and clinical data ingestion/processing on AWS, including real-time streaming and batch pipelines. Delivered measurable outcomes: 20M daily transactions processed, latency cut from 4 hours to 5 minutes, ~70% fewer failures, and 120+ pipelines running at 99.8% reliability with full audit compliance.”

“GenAI/LLM ML engineer (currently at Webprobo) building an enterprise GenAI platform with document intelligence and automation on AWS and blockchain. Has hands-on experience with RAG, LLM evaluation tooling, and orchestrating production LLM workflows with Apache Airflow, plus deep exposure to reliability challenges in globally distributed/edge deployments. Also partnered with business/marketing stakeholders at a banking client to deliver an AI-driven customer retention insights solution.”

“Built and deployed a production LLM-powered customer support assistant using a RAG backend in Python, focused on deflecting repetitive Tier-1 tickets and reducing resolution time. Demonstrates strong production engineering instincts around reliability (confidence scoring + human fallback), scalability/cost optimization (multi-stage pipelines), and workflow orchestration/observability (LangChain, custom DAGs, structured logging, step metrics).”

“Backend engineer who designed and evolved an AWS-based event-processing system in Python/PostgreSQL, achieving a 60% p95 latency reduction while improving reliability during traffic spikes. Led a zero-downtime migration from a monolithic Django app to FastAPI microservices using feature flags, strong testing, and cross-team coordination, with production-grade observability (Prometheus/Grafana/CloudWatch) and security (JWT/OAuth2, RBAC, Postgres RLS).”

“LLM/agent engineer who has deployed a production internal assistant to reduce employee inquiry resolution time while maintaining regulatory compliance. Experienced with RAG, hallucination risk triage, and graph-based orchestration (LangGraph) for enterprise/banking-style workflows, emphasizing schema-validated, citation-backed, tool-constrained agent designs and tight collaboration with non-technical business/compliance stakeholders.”

“Backend engineer with Citi Bank experience building and operating a Python/Flask Personal Finance Manager platform at 1M+ transactions/month. Strong in secure API design, database performance tuning (PostgreSQL/Azure SQL), and production reliability (92%+ test coverage, load testing, monitoring). Also integrated an NLP expense-tagging microservice with caching, background workers, autoscaling, and multi-tenant isolation via RLS and tenant-aware JWT.”

“Built and deployed a production LLM-powered clinical note summarization system used by care managers to speed review of 5–20 page unstructured medical records. Implemented safety-focused validation (prompt constraints, rule-based and section-level checks, human-in-the-loop) to reduce hallucinations while maintaining low latency and meeting privacy/regulatory constraints, integrating via APIs into existing clinical tools.”

“AI/LLM engineer with production experience building secure, scalable compliance-focused generative AI systems (GPT-3/4, BERT) including RAG over internal regulatory document bases. Has delivered end-to-end pipelines on AWS with PySpark/Airflow/Kubernetes/FastAPI, emphasizing privacy controls, monitoring, and iterative evaluation (A/B testing). Also partnered closely with bank compliance officers using prototypes to refine NLP summarization/classification and reduce document review time.”

“Backend/Python engineer who owned an end-to-end FastAPI + AWS internal natural-language document Q&A system (Textract extraction, embeddings/vector DB, LLM integration) with strong focus on reliability and latency. Hands-on with Kubernetes + GitOps (Argo CD, Helm, rolling updates/auto-rollback) and built/optimized Kafka streaming pipelines using Prometheus/Grafana. Also supported a zero-downtime on-prem to cloud migration with parallel run and gradual traffic cutover.”

“Product-leaning full-stack engineer (65% product / 35% infra) who built core components of the LightFoot feature flag platform: end-to-end client/server SDKs with OpenTelemetry-based observability and a React+TypeScript UI for flag management and metrics dashboards. Strong focus on performance (memoization/lazy loading/caching), reliable API design, and Postgres modeling for read-heavy flag evaluation workloads, with AWS production experience (EC2/ECS/Lambda/API Gateway/VPC).”

“AI engineer who shipped a production chat assistant for a storage company by building the underlying RAG-style knowledge base (document ingestion, chunking/embeddings, FAISS vector store) and an admin update interface to keep content current. Also has full-stack delivery experience (Python REST APIs + React/TypeScript UI) and AWS operations using Terraform/Jenkins, including handling a real production performance incident by optimizing DB queries and adding auto-scaling.”

“Full-stack/backend engineer with deep experience building real-time fraud and credit-risk systems. Shipped an event-driven fraud monitoring platform (Kafka→MongoDB/Redis→WebSockets) delivering sub-200ms updates to 3000+ concurrent internal users, and built a Java/Spring Boot credit risk decisioning API that improved turnaround time by 30–40%. Strong AWS production operations (ECS Fargate/RDS/Redis) with proven incident response and performance tuning.”

“Entry-level software engineer who has shipped end-to-end product features in a chat application, including a frontend table component plus backend support, then refactored the implementation after client feedback by switching UI libraries. Has production experience combining traditional NLP with an LLM fallback based on confidence thresholds for intent/entity extraction, and is building infrastructure around legacy enterprise APIs (MCP tools) including asynchronous job queues for long-running tasks.”

“Data engineer/backend data services practitioner with Bank of America experience building real-time and batch transaction-monitoring pipelines and APIs (Kafka + databases, REST/GraphQL). Highlights include a reported 45% response-time improvement through performance optimizations and use of Delta Lake schema evolution plus CI/CD (GitHub Actions/Jenkins) and operational reliability patterns like CloudWatch monitoring and dead-letter queues.”