AI/ML Engineer — Multi-Agent Systems

Role overview Develop the machine learning systems that let multiple agents coordinate on complex tasks, retain useful context, and follow reasoning workflows. The work combines system design, retrieval, model optimization, and evaluation, with a focus on turning user needs into dependable agent capabilities. This is a full-time remote position.

Responsibilities - Design coordination protocols for agents handling multi-step tasks. - Build retrieval-augmented generation pipelines for agent memory and persistent context. - Fine-tune and optimize language models for operational tasks and reasoning workflows. - Research and implement methods for evaluating agent performance and reliability. - Work with product teams to translate user requirements into agent capabilities.

Requirements - At least three years of AI/ML engineering experience focused on NLP or multi-agent systems. - Strong Python skills and experience with PyTorch or JAX. - Experience with LLM orchestration frameworks and prompt engineering. - Understanding of vector storage and semantic retrieval architectures. - A master’s or doctoral degree in computer science or AI, or equivalent industry experience.

Nice to have - Experience with reinforcement learning or autonomous systems. - Research published at leading AI conferences. - Experience deploying large-scale machine learning models in production.