Senior Staff Machine Learning Engineer, AI Agent Platform

What you'll do

• Define the long-term technical strategy and architecture for the multi-tenant AI agent platform.
• Architect an enterprise skill ecosystem including reusable capability packages and a governed internal marketplace.
• Lead the design of production-grade harness systems for tool dispatch, context management, and error recovery.
• Develop context engineering systems involving memory hierarchies, RAG pipelines, and dynamic information management.
• Build high-performance infrastructure for multi-agent orchestration, prompt management, and observability pipelines.
• Establish AI safety frameworks including guardrails, human-in-the-loop escalation, and security vetting for agent skills.
• Mentor engineers and establish best practices for AI engineering across the organization.

What we're looking for

• Bachelor's degree in CS, Engineering, or a related field; an advanced degree is highly desirable.
• 8+ years of professional software development experience using at least two languages such as Java, C++, Python, Go, or C#.
• 6+ years of experience designing and building AI/ML platforms using open-source or cloud-agnostic components.
• 5+ years of experience managing end-to-end SDLCs including CI/CD, Kubernetes, testing, monitoring, and production support.
• 4+ years of experience building training, fine-tuning, and inferencing systems for LLMs on GPU infrastructure.
• 3+ years of experience designing and operating multi-agent or agentic AI systems in production.
• Demonstrated track record of leading technical initiatives, setting architectural direction, and mentoring across teams.
• Strong expertise in context engineering, including RAG pipelines, memory architectures, and advanced LLM guardrail frameworks.