Teams at Sovos

Lead technical direction for Sovos's AI Platform and LLMOps practice: set architecture, guardrails, observability, model and prompt strategies, enable teams through workshops and tooling, and mentor engineers to scale agentic and LLM-based systems into production.

Design, scale, and optimize Sovos production infrastructure. Manage on-prem datacenter systems, automate provisioning with Terraform, maintain CI/CD in Azure DevOps, operate Kubernetes/Docker Swarm, and implement observability and alerting using the Grafana LGTM stack. Participate in on-call rotation, troubleshoot incidents, document processes, and support high availability.

Lead LLMOps initiatives to scale and govern generative AI: define AI quality standards, manage prompt and model versioning, coordinate safety/red team testing, implement observability for latency/cost/quality using tools like Langfuse, manage Jira workflows, develop playbooks, and lead AI incident response and root-cause analysis.