Available now · Hoffman Estates, IL (Chicago area)
Senior DevOps / SRE Engineer — 10 years across AWS, Azure & GCP, now building AI engineering systems
I design and operate cloud infrastructure that stays up: multi-region disaster recovery, Kubernetes platforms, and release automation for regulated financial-services systems. Lately I've been applying that same reliability discipline to AI systems — retrieval pipelines, agent tooling, and the evaluation harnesses that keep them honest.
Problem: when a pod crash-loops or a service degrades, on-call engineers lose time manually correlating Kubernetes resource changes, logs, and runbooks before they can even start fixing anything.
Approach: built a PydanticAI investigation agent with five read-only tools that pulls Kubernetes resource history and deduplicated logs against Elasticsearch-indexed evidence, forces every claim to cite a concrete source, and separates confirmed observations from hypotheses so it never asserts something it didn't actually see.
Outcome: validated with 22 automated tests across three failure scenarios and a 30-case benchmark tracking retrieval quality, latency, and cost.
Problem: a small retailer needed to take orders conversationally against live, changing inventory without a person picking up every call or chat.
Approach: built a LangChain/LangGraph conversational ordering flow backed by a RAG pipeline over live product and inventory data, deployed on Cloudflare Workers with Stripe checkout built directly into the flow so an order could close without a handoff.
Outcome: delivered and running in production for a paying client.
20+ Terraform stacks across primary and DR regions, cross-region S3 replication with zero-downtime failover, incident response and release automation across 12+ microservices.
Led IaC initiative automating VM provisioning across 4 global datacenters; converted PowerShell automation into Jenkins CI/CD pipelines.
Owned disaster recovery for an AWS ETL pipeline; defined SLIs, SLOs, and error budgets for the platform.
Lambda-to-Airflow migration; Terraform-provisioned Airflow infrastructure.
Multi-cloud delivery across insurance, animal health, automotive, and industrial clients on AWS, Azure, and GCP.
CI/CD pipelines with Jenkins and Docker; AWS IAM, RDS, and Auto Scaling management.
Ten years of DevOps work didn't tell me what an AI engineer's day-to-day looks like, so I enrolled in a hands-on buildcamp to find out. Here's what building a retrieval pipeline from scratch actually involved, and where my reliability instincts helped and where they didn't.