AI Tooling and Infrastructure Engineer
Core
Build and operate infrastructure to integrate existing LLMs and AI tooling into internal tools and customer-facing products for technical training and documentation.
Role type
Senior IC AI Infrastructure Engineer
Builds
Reliable, scalable systems for content generation, documentation search/retrieval, automated QA, and Avatar-led training
Domain
Enterprise Networking / Technical Training & Documentation
Deliverable
production ML models
Required skills
Python, Java, cloud infrastructure (AWS/GCP/Azure), infrastructure-as-code, containers, Linux/Windows server operations, web services (APIs/backend), vendor API integration, observability, cost management
Preferred skills
LLM observability/eval tooling, self-hosted models/inference, automation, telemetry, network/systems infrastructure
Technologies
LLM APIs, retrieval-augmented generation, agentic tooling, MCP, orchestration layers, retrieval systems, evaluation harnesses
Responsibilities
Design and operate infrastructure integrating LLMs into tools; evaluate and maintain third-party AI platforms; build custom pipelines and monitoring; ensure operational reliability (uptime, latency, cost); implement guardrails for cost and prompt management; collaborate with stakeholders to translate use cases into systems; set up telemetry; contribute to AI adoption standards
Seniority
Senior, hands-on IC
