Agentic AI, Engineer

Role overview

Key responsibilities

• Architect and deploy agentic AI systems integrating agents with foundation models, enterprise systems, third-party tools, and APIs.
• Build RAG, memory, and reasoning pipelines grounded in reliable real-world data.
• Design workflows for planning, delegation, tool selection, handoffs, inter-agent communication, and human oversight.
• Optimize orchestration for autonomy, latency, cost, interpretability, reliability, and maintainability.
• Collaborate with AI, application engineering, MLOps, and product teams to move solutions from prototype to production.
• Monitor, evaluate, and benchmark agent performance and help ensure safe, accurate, trustworthy, and observable systems.
• Document architectures, communication flows, guardrails, context engineering, memory, tool interfaces, and orchestration logic.
• Stay current with agentic AI, RAG, model-context protocols, evaluation, and AI safety.

Required qualifications

• Bachelor's or Master's degree in a relevant computer science, artificial intelligence, machine learning, data science, or software engineering field.
• 2+ years of hands-on experience developing agentic AI systems, LLM-powered applications, or advanced generative AI solutions.
• Contributions to open-source agentic AI frameworks, orchestration platforms, evaluation tooling, or agent communication protocols.
• Experience building microservices and deploying AI applications on AWS, Azure, or Google Cloud Platform.
• Experience with AI safety, guardrails, observability, traceability, evaluation, and explainability.
• Experience deploying LLM or agentic workloads using containers, Kubernetes, CI/CD, and MLOps or LLMOps practices.

Preferred experience

• 5+ years of overall professional software engineering experience is preferred.

Workplace

• The listed workplace is on-site at the employer's headquarters.