AI Engineer – Agentic

Job Summary

Join Nabeh as an Agentic AI Engineer to design, build, and deploy agentic AI systems that plan, reason, and act. You will work on single-agent and multi-agent systems, orchestrating workflows involving retrieval-augmented generation, context engineering, reasoning, tool calling, memory, and inter-agent communication.

Responsibilities

• Architect, build, and deploy agentic AI systems integrating AI agents with foundation models, enterprise systems, third-party tools, and APIs using agentic frameworks or custom orchestrators
• Build and maintain retrieval-augmented generation (RAG), memory, and reasoning pipelines to ground agent decisions in reliable data and enable persistent, contextual behavior
• Design single-agent and multi-agent workflows including planning, delegation, tool selection, handoffs, inter-agent communication, and human-in-the-loop controls
• Optimize orchestration and reasoning performance while balancing autonomy, latency, cost, interpretability, reliability, and maintainability
• Collaborate with Generative AI engineers, application engineers, MLOps engineers, and product teams to move agentic AI solutions from prototype to production
• Monitor, evaluate, and benchmark agent performance to ensure AI systems are safe, accurate, trustworthy, observable, and deliver high-quality user experience
• Document agent architectures, communication flows, guardrails, context-engineering strategies, memory design, tool interfaces, and orchestration logic
• Stay current with advances in agentic AI, multi-agent orchestration, RAG, model-context protocols, cognitive architectures, evaluation methods, and AI safety mechanisms

Requirements

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Software Engineering, or related field
• 2+ years of hands-on experience developing agentic AI systems, LLM-powered applications, or advanced Generative AI solutions
• 5+ years of overall professional software engineering experience preferred
• Contributions to open-source agentic AI frameworks, orchestration platforms, evaluation tooling, or agent communication protocols preferred
• Experience building microservices and deploying AI applications on AWS, Azure, or Google Cloud Platform (GCP)
• Experience with AI safety, guardrails, observability, traceability, evaluation, and explainability for agentic AI systems
• Experience deploying LLM or agentic workloads in production using containers, Kubernetes, CI/CD pipelines, and modern MLOps or LLMOps practices

We refresh listings regularly, but some roles close early on the source platform.