Remote AI Research Engineer - Agentic Post-Training

YO AI Labs; La Pampa; A distancia; ARS 200.037.000 - 292.362.000; Jornada completa

Descripción de la vacante

Tether is seeking an AI Research Engineer focused on post-training for agentic workflows. You will refine pre-trained models to improve reasoning, planning, and autonomous tool invocation on edge devices. The role spans a range of systems from efficient agents to multi-modal architectures, with emphasis on tool use and RLHF.

Join a globally distributed team driving fintech AI innovations. Excellent English communication and a track record in open-source agentic AI work are valued.

Formación

• Degree in Computer Science, ML, or related field required.
• Advanced degree (MS/PhD) preferred.
• Experience with post-training for agentic workflows is essential.

Responsabilidades

• Conduct end-to-end research and engineering to advance post-training of agentic and tool-use models to achieve SOTA results.
• Drive improvements in factuality, instruction adherence, tool/function 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 rigorous evaluation suites and diagnostic tools to assess model readiness for deployment.
• Strengthen feedback loops from real-world usage to improve post-training processes.

Conocimientos

LLM architectures

Agentic post-training

Tool-use fine-tuning

Reinforcement learning from feedback

Data curation

Educación

Degree in Computer Science or Machine Learning or related field

Advanced degree (MS/PhD) preferred

Herramientas

GitHub

Hugging Face

Descripción del empleo

Tether is seeking an AI Research Engineer focused on post-training for agentic workflows. You will refine pre-trained models to improve reasoning, planning, and autonomous tool invocation on edge devices. The role spans a range of systems from efficient agents to multi-modal architectures, with emphasis on tool use and RLHF.

Join a globally distributed team driving fintech AI innovations. Excellent English communication and a track record in open-source agentic AI work are valued.