Role: Lead AI Engineer, Agent Systems
Location: Hybrid in Palo Alto, CA
Full Time Employment
 
About the role

• We are seeking a Lead AI Engineer, Agent Systems to join the AI Research Incubation Team.
• In this role, you will design and build production-grade AI agent systems that translate cutting-edge research into scalable, reliable platform capabilities.
• You will work closely with AI researchers, platform engineers, and product teams to develop agent orchestration frameworks, tool integration, and runtime control systems. This role focuses on system-level intelligence, not on inventing new models, but on making AI agents robust, observable, and controllable in real-world environments.
• This is a lead-level individual contributor role with strong technical ownership and cross-team influence.

 
Duties

• Design and build AI agent systems, including agent lifecycle management, orchestration, and execution control.
• Develop scalable pipelines for tool invocation, agent planning, memory, and state management.
• Collaborate with AI researchers to operationalize research outputs into reliable agent behaviors.
• Define and enforce best practices for agent reliability, safety, observability, and cost control.
• Lead the design of APIs and services supporting agent runtime and coordination.
• Drive architectural decisions for agent frameworks and integrations across AI services.
• Troubleshoot complex system-level issues involving agent behavior, performance, or failure modes.
• Mentor engineers and provide technical leadership within the AI engineering organization.

 
Required Skills

• Bachelor’s degree in Computer Science, Software Engineering, or a related field.
• 5+ years of experience in backend or distributed systems engineering, with increasing technical ownership.
• Strong proficiency in Python, with experience designing complex backend services.
• Experience building production systems involving LLMs, AI services, or agent-like workflows.
• Deep understanding of RESTful APIs, service-oriented architectures, and system scalability. Kubernetes).
• Experience with cloud platforms (AWS, GCP) and containerized environments (Docker,
• Strong debugging skills across distributed systems, including logs, traces, and metrics.
• Excellent communication skills and the ability to collaborate across research and engineering teams.

 
Preferred

• Hands-on experience with AI agent frameworks, workflow engines, or orchestration systems.
• Familiarity with RAG systems, vector databases, or memory architectures.
• Experience implementing safety guardrails, policy enforcement, or AI observability.
• Exposure to event-driven architectures and message queues (Kafka, RabbitMQ).
• Prior experience in a research-adjacent or incubation environment.

 
 
At SPECTRAFORCE, we are committed to maintaining a workplace that ensures fair compensation and wage transparency in adherence with all applicable state and local laws. This position’s starting pay is: $ 185000.00/Yearly.