Staff Software Engineer, AI Platform

This is a fully remote position, open to applicants in Illinois.

📋 Description

• Take ownership of key components of the AI platform from API design through performance under load.

• Guarantee reliability and performance of the AI gateway in a production environment.

• Develop provider abstraction, implement model routing, failover strategies, and configuration-driven provider switching.

• Create an agent surface that is agnostic to both the framework and deployment location.

• Establish evaluation and benchmarking capabilities largely from the ground up.

• Design enforceable guardrails to ensure the safe deployment of agents in production.

• Oversee inference costs and latency, including spend attribution and routing decisions.

• Maintain the model onboarding process in response to changes in the model landscape.

• Ensure that the compliant path is the expedited route for architecture, security, and responsible-AI evaluations.

• Tackle complex integration challenges for other engineering teams.

• Enhance observability in anticipation of scaling needs.

• Mentor a distributed team while producing durable designs and comprehensive documentation.

• Define technical direction and select platform abstractions and scope.

⛳️ Requirements

• Minimum of 8 years of experience in building and operating production systems.

• Proven track record of deploying agentic systems to production, including experience with agentic patterns, retrieval, tool invocation, inference cost, and latency.

• Practical experience with multiple model providers and managing practical differences among them.

• Familiarity with evaluation, observability, or guardrail tools designed for agentic systems.

• Strong history in platform engineering within systems utilized by other engineering teams.

• In-depth hands-on experience with at least one major public cloud, including managing and troubleshooting production workloads.

• Skilled in designing APIs and abstractions that others rely on, ensuring they remain stable.

• Proven ownership in production environments, including on-call duties, incident response, and root cause analysis.

• History of effectively navigating processes and facilitating decisions within a large organization.

• Exceptional communication skills in English, both written and verbal.

• Must possess authorization to work in the United States without sponsorship.

• Preferred: experience with internal developer platforms or shared multi-tenant services.

• Preferred: familiarity with Kubernetes and container-based delivery.

• Preferred: knowledge of infrastructure as code principles.

• Preferred: experience with enterprise security, data privacy, or responsible-AI review processes.

🏝️ Benefits

• 401(k) plan with company matching contributions.

• Comprehensive medical, dental, and vision care coverage.

• Paid parental leave at 100% of salary.

• Generous paid time off and company holidays.

• Early access to earned wages through Daily Pay.