3 months ago
Responsibilities
- Design and build a vendor-agnostic agent platform for multiple workflows.
- Develop evaluation and reliability frameworks to enhance agent performance.
- Implement safety and governance controls for responsible agent behavior.
- Create systems for data grounding and memory to ensure accuracy and context-awareness.
- Prototype and productionize agent behaviors using real workflows.
- Collaborate with product and engineering teams to identify and launch agent-powered workflows.
- Define best practices and mentor other engineers on secure and scalable agent systems.
- Contribute to the team's strategy and roadmap by informing architecture choices.
Requirements
- 5+ years of professional software engineering experience in distributed systems.
- 3+ years of experience with production-grade systems focusing on reliability and performance.
- Hands-on experience with LLMs or Agentic AI systems in production.
- Ability to operate in ambiguity and build from first principles.
- Strong product and systems thinking connecting technical decisions to real-world impact.
- Familiarity with AI safety, security, or policy systems.
- Proficiency in a modern backend programming language and cloud-native infrastructure.
- Experience collaborating with cross-functional partners on technical initiatives.