ml engineer Agents

eBay is a global ecommerce platform connecting buyers and sellers in more than 190 markets. Its Search & Recommendations team delivers large-scale, near-real-time personalized recommendations across web and native app platforms, including agentic workflows, deep learning retrieval systems, machine-learned ranking models, and advanced MLOps.

• Design and architect robust, multi-step multi-agent systems across customer-facing eBay surfaces;
• Build and evaluate architectures where multiple agents coordinate, delegate, and communicate to solve complex user intents;
• Investigate and implement techniques for agent interaction patterns, including structured communication protocols, reflection loops, evaluator-generator frameworks, and tool-augmented reasoning;
• Address latency optimization, cost management, safety and guardrails, and cascading failures in multi-agent production systems;
• Use large-scale unstructured and multimodal inventory datasets to improve core marketplace metrics through A/B testing of autonomous user experiences;
• Collaborate with applied researchers and engineers specializing in NLP, large language models, AI, agentic workflows, recommender systems, and ML production engineering.

• MS/PhD in Computer Science or a related area;
• 5+ Years of relevant work experience in Machine Learning, AI, or ML Engineering;
• Experience researching, building, or studying systems where multiple agents interact, exchange information, critique reasoning, and coordinate decisions over time, such as ReAct, tool-calling loops, and planning systems;
• Extensive development experience in an ML/AI technology environment;
• Experience with Python and PyTorch;
• Experience using cloud services, big data pipelines, and databases in an industrial setting;
• Experience in Natural Language Processing (NLP) and industrial recommender systems;
• Nice to have: No preferred qualifications specified.

• Amsterdam, North Holland, Netherlands.