Clera
Agent Systems Engineer
remote (Remote)$180k–$250kfulltimemidAdded today
About this role
Design and build production-grade multi-agent systems infrastructure for an enterprise AI platform serving regulated industries. This high-ownership role focuses on agent orchestration, behavioral modeling, and translating agent outputs into actionable insights at scale.
What you'll do
- Design long-running multi-agent architectures including topologies, orchestration, memory management, and tool registries
- Develop behavioral and persona models with goal-directed simulations and evaluation frameworks
- Build signal and insight systems to translate agent outputs into product decisions
- Ensure production reliability through tracing, cost monitoring, failure detection, and fallback strategies
- Collaborate with distributed systems, ML, and product teams on scalable agent capabilities
What they're looking for
- Multi-agent systems architecture and orchestration
- Python with async programming expertise
- Production ML systems (tracing, cost monitoring, failure detection)
- Docker and Kubernetes containerization
- Behavioral modeling and evaluation framework design
- Signal extraction and data-driven product insights
- Distributed systems design
- Cross-functional collaboration
Benefits
- Salary: $180,000–$250,000 USD annually (location-dependent)
- Hybrid working arrangement
- International location options for exceptional candidates
- High-impact role with individual ownership
- Access to well-funded enterprise AI platform
Opens the official application on the employer’s site. No login required.
Clera
Clera builds an agentic operating system that automates complex workflows and processes through AI agents, with a platform designed to simplify distributed infrastructure management for developers. The company is hiring Founding Engineers, Customer Engineers, and Product Engineers to develop both backend systems and user-facing interfaces across their AI automation products.
View all jobs at CleraLikely interview questions
- Walk us through a multi-agent system you've built in production—how did you handle orchestration, memory management, and failure recovery?
- Describe your experience designing evaluation frameworks for agent behavioral fidelity. How did you surface and address failure modes?