Remote AI Research Engineer — Agentic Post-Training

Alignerr Corp.; Santa Fe Capital; A distancia; ARS 215.229.000 - 276.723.000; Jornada completa

Descripción de la vacante

Tether is seeking an AI Research Engineer focused on agentic post-training to advance tool use, reasoning, and autonomous decision-making on edge devices. You will work on a range of systems from lightweight agents to multimodal architectures, optimizing for tool-augmented decision making.

The role requires deep expertise in LLMs, post-training workflows, and distributed training frameworks, with a hands-on, research-driven approach to developing new algorithms that enable goal-directed behavior

Formación

• Experience with post-training for agentic workflows and tool use.
• Strong publication record in AI conferences preferred.
• Experience with multimodal post-training workflows and data pipelines.
• Hands-on experience with large-scale distributed training environments.

Responsabilidades

• Conduct end-to-end research to advance post-training of agentic models.
• Improve factuality, instruction adherence, and tool usage in models.
• Design and enhance post-training systems, data pipelines, and evaluation frameworks.
• Develop evaluation suites and diagnostic tools for model readiness.

Conocimientos

Large language models

Agentic workflows

Tool use

Reinforcement learning from feedback

Multimodal systems

Educación

MS/PhD preferred

Herramientas

GitHub

Hugging Face

Distributed training

Descripción del empleo

Tether is seeking an AI Research Engineer focused on agentic post-training to advance tool use, reasoning, and autonomous decision-making on edge devices. You will work on a range of systems from lightweight agents to multimodal architectures, optimizing for tool-augmented decision making.

The role requires deep expertise in LLMs, post-training workflows, and distributed training frameworks, with a hands-on, research-driven approach to developing new algorithms that enable goal-directed behavior