I'm an AIOps and Cloud Infrastructure Engineer who's taken AI-enabled systems from prototype to production across enterprise and freelance environments. At Thomson Reuters, I work on production AI workloads including agentic services, Bedrock and Anthropic API integrations, server-sent-event streaming, pgvector-based document ingestion, embedding pipelines, and async knowledge-graph processing. I also support infrastructure modernization through Pulumi-based provisioning, remote state management with S3/DynamoDB, cross-account migration work, and production verification across IAM, networking, databases, service health, and CI/CD.
I bring a strong operations background from application support, SRE-style incident response, and observability engineering. I've owned on-call responsibilities, led post-mortems for production incidents, and improved monitoring across New Relic, Datadog, ELK, and custom tooling. I've reduced operational toil through Python, Bash, SQL, and workflow automation. My work focuses on making systems easier to operate by improving alert quality, documenting runbooks, automating repeatable tasks, and feeding production lessons back into infrastructure-as-code and deployment pipelines.
Alongside enterprise engineering, I've delivered full-stack and AI-first products for freelance clients across React, FastAPI, MERN, Docker, cloud deployments, and LLM APIs—including marketplaces, case-management systems, workforce tools, AI assistants, trading platforms, and an AWS visual designer that emits IaC. This combination of AI engineering, cloud infrastructure, CI/CD, observability, and hands-on product delivery lets me bridge development, operations, and platform reliability in fast-moving technical environments.