Applied AI Engineer - Agents
Core
Human-in-the-loop training and evaluation of autonomous AI agents to improve their reasoning, security, and workflow capabilities.
Role type
Applied AI Engineer - Agents (Human Feedback & Evaluation)
Builds
Proactive, multi-step autonomous agents for complex real-world workflows
Domain
Generative AI, Autonomous Agents, System Orchestration
Deliverable
production ML models | research
Required skills
Backend engineering, AI automation, complex system integration, multi-turn system interaction handling, multi-stage coordination workflow design, live tool and API integration, persistent state and session tracking, security and privacy risk identification
Preferred skills
Experience with orchestration, software development, human feedback on agent behavior
Technologies
Java, JavaScript, Python, SQL, Supabase, Gmail
Responsibilities
Provide human feedback on agent behavior to train advanced generative AI systems, Evaluate system performance in live scenarios, Identify weaknesses in agent behavior including security, privacy, and reasoning failures, Design and coordinate complex real-world architectural workflows, Connect agents to live tools and APIs to solve practical problems, Monitor agent progress using session tracking mechanisms