Vetted Observability Professionals

“Backend engineer who built and evolved a low-latency document search platform (C++/gRPC on Kubernetes with a vector database), emphasizing resilience under concurrent load through strict deadlines, retries, idempotency, and observability. Also experienced building secure, frontend-friendly FastAPI services (Pydantic + JWT) and executing safe incremental refactors using feature flags and parallel validation.”

“Built and shipped a production AI-driven privacy automation system that autonomously navigates data broker sites to submit opt-out/data deletion requests end-to-end, including robust CAPTCHA detection/solving (e.g., reCAPTCHA/hCaptcha/Cloudflare) via 2Captcha. Experienced in orchestrating stateful LLM agent workflows with LangGraph and hardening them for production with strict state management, retries/fallbacks, validation layers, and database-backed observability/audit logs, collaborating closely with legal/compliance stakeholders.”

“Backend engineer who built and scaled AmazonProAI, a multi-tenant SaaS platform for Amazon sellers, using a modular Django/DRF monolith with strict seller-level isolation and security controls. Led a controlled SQLite-to-PostgreSQL migration and hardened bulk Excel ingestion with idempotency and data integrity constraints to prevent duplicate metrics and noisy alerts while keeping the system ready for future service extraction.”

“AI/LLM engineer who has owned end-to-end production delivery of multi-agent RAG systems on Azure (React + FastAPI + data pipelines + Terraform), including rigorous evaluation/monitoring and reliability guardrails. Shipped an AI-driven observability root-cause analysis assistant that reduced MTTR ~30%, cut alert noise ~20%, and reached ~70% adoption in the first month; also built a clinical document Q&A system with citations and compliance-oriented controls.”

“LLM/AI backend engineer with hands-on experience taking customer LLM prototypes into production using FastAPI, containerization, CI/CD, and OpenTelemetry-based observability. Demonstrated measurable impact by cutting LLM costs ~40% and reducing workflow errors ~50% through schema-enforced outputs, better tool definitions, retries, and prompt/model optimization; also supports pre-sales via technical discovery and rapid integration demos.”

“Backend/infrastructure engineer in the EBS org focused on global server lifecycle and fleet reliability. Led a major modernization from manual, ticket-driven recovery to centralized Python services and operator tooling with DynamoDB-backed state, strong auth/allowlisting, and CloudWatch monitoring, plus an AWS Glue/S3/SNS data pipeline to join server and hardware datasets for global operational querying and automated recovery.”