About the Role
We are looking for a Platform Engineer to help build and operationalize our AI tooling ecosystem. Working closely with the Team Lead and Senior/Staff SWE, you will be the hands-on integrator connecting external cloud AI providers, internal models, and end-user tools into our unified control plane.
The unified AI Platform Team builds the centralized software, operations, and governance layers that safely route users to the most cost-effective models, addressing the firm's "Dual Mandate": providing low-friction access to the best frontier AI tools while strictly managing an exponentially growing cost curve.
- Configure and manage multi-engine API gateways, implementing dynamic routing rules, rate limits, and fallback logic for LLM requests.
- Execute the technical migration and integration of firm-wide tools into our centralized management plane to ensure all AI traffic is securely logged and governed.
- Operate within our Shared Responsibility Model alongside the Cloud team to manage AI services deployed in enterprise landing zones (e.g., managing Azure OpenAI instances, model deployments, and API key generation).
- Write robust Go and Python code to support the continuous sync loop for our usage dashboard and implement automated "progressive friction" mechanisms, such as alerts.
- Partner with the Inference Infrastructure pod to ensure our self-hosted, on-premise models are successfully registered and routable within our AI gateways.
Responsibilities
- Configure and manage multi-engine API gateways, implementing dynamic routing rules, rate limits, and fallback logic for LLM requests.
- Execute the technical migration and integration of firm-wide tools into our centralized management plane to ensure all AI traffic is securely logged and governed.
- Operate within our Shared Responsibility Model alongside the Cloud team to manage AI services deployed in enterprise landing zones (e.g., managing Azure OpenAI instances, model deployments, and API key generation).
- Write robust Go and Python code to support the continuous sync loop for our usage dashboard and implement automated "progressive friction" mechanisms, such as alerts.
- Partner with the Inference Infrastructure pod to ensure our self-hosted, on-premise models are successfully registered and routable within our AI gateways.
Requirements
- Strong backend programming experience, specifically in Go and/or Python.
- Hands-on experience with API design, integration, and platform/cloud engineering concepts.
- Familiarity with API gateways, proxy configuration, or distributed system networking.
- A strong interest in the rapidly evolving LLM ecosystem and the technical mechanics of AI tooling.
- A collaborative mindset with a focus on writing clean, maintainable code to replace prototype systems.