Remote AI Research Engineer — Agentic Post-Training

YO AI Labs; Neuquén; A distancia; ARS 184.482.000 - 276.723.000; Jornada completa

Descripción de la vacante

Tether is seeking an AI Research Engineer to push post-training methods for agentic, tool-using models. You will refine pre-trained models to reason, plan, and autonomously invoke external tools on edge devices, addressing multi-step tasks.

Join a cross-functional team focused on scalable, multimodal systems and distributed training, delivering state-of-the-art capabilities with real-world impact.

Formación

• Deep expertise in large language model architectures and substantial experience in post-training for agentic workflows.
• Experience with multimodal post-training workflows and data pipelines for agentic systems and tool use.
• Hands-on experience applying post-training at scale using distributed training frameworks (e.g., multi-node GPU environments).
• Open-source contributions related to agentic systems or tool use on platforms such as GitHub or Hugging Face.
• Publications at leading AI conferences (e.g., NeurIPS, ICML, ICLR, ACL, CVPR, ECCV).

Responsabilidades

• Conduct end-to-end research and engineering initiatives to advance post-training of agentic and tool-use models to achieve SOTA results.
• Drive cross-cutting model improvements including factuality, instruction adherence, tool use, multi-agent coordination, and reasoning calibration.
• Design and enhance large-scale post-training systems, including data pipelines, training workflows, evaluation frameworks, and benchmark infrastructure.
• Develop robust evaluation suites and diagnostic tools to assess model readiness for deployment.
• Strengthen feedback loops from real-world product usage, incorporating user signals into post-training.
• Collaborate with tooling, product, and training teams to improve usefulness, reliability, and agentic capabilities of frontier models.
• Closely liaise with research and cross-functional teams to determine production-ready integrations for major model releases.

Conocimientos

Large language models

Agentic workflows

Tool use fine-tuning

Reinforcement learning from feedback

Educación

PhD preferred in CS/ML

Advanced degree (MS/PhD)

Herramientas

GitHub

Hugging Face

Descripción del empleo

Tether is seeking an AI Research Engineer to push post-training methods for agentic, tool-using models. You will refine pre-trained models to reason, plan, and autonomously invoke external tools on edge devices, addressing multi-step tasks.

Join a cross-functional team focused on scalable, multimodal systems and distributed training, delivering state-of-the-art capabilities with real-world impact.