Platform Engineer - AI Engineering

Job summary

The Platform Engineer builds and operates a centralized AI tooling platform that connects cloud AI providers, internal models, and end-user tools while managing costs and governing AI traffic. The role configures API gateways, routing, rate limits, and fallbacks; integrates tools and Azure OpenAI services; develops Go and Python automation; and works with inference infrastructure teams to make self-hosted models routable.

Qualifications

• Strong backend programming experience in Go and/or Python.
• Hands-on experience with API design, integration, and platform or cloud engineering.
• Familiarity with API gateways, proxy configuration, or distributed systems networking.
• Interest in the LLM ecosystem and AI tooling.
• Collaborative approach and commitment to clean, maintainable code.

Responsibilities

• Configure multi-engine API gateways, including dynamic routing, rate limits, and fallback logic for LLM requests.
• Migrate and integrate firm-wide tools into a centralized management plane for secure logging and governance of AI traffic.
• Manage AI services in enterprise cloud landing zones, including Azure OpenAI instances, model deployments, and API key generation.
• Develop Go and Python code for usage dashboard synchronization and automated alerts.
• Register self-hosted, on-premises models with AI gateways and enable routing.

Skills

Languages

Industry

Relocation