Remote Agentic AI Research Engineer (Post-Training)

YO AI Labs; La Pampa; A distancia; ARS 230.602.000 - 322.843.000; Jornada completa

Descripción de la vacante

Tether is seeking an AI Research Engineer to advance agentic post-training, focusing on agent behaviors and tool invocation across edge devices. You will refine pre-trained models for reasoning, planning, and autonomous tool use, from mobile to server scale.

The role covers multimodal systems, distributed training, evaluation, and collaboration with cross-functional teams. You will publish in top AI venues and contribute open-source work.

Formación

• PhD preferred with strong publication record in top AI conferences.
• Experience with multimodal post-training workflows and data pipelines.
• Hands-on experience applying post-training at scale using distributed training frameworks (multi-node GPUs).
• Demonstrated open-source contributions related to agentic systems or tool use.

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, and multi-agent coordination.
• Design and enhance large-scale post-training systems, data pipelines, training workflows, evaluation frameworks, and benchmarks.
• Develop rigorous evaluation suites and diagnostic tools to assess model readiness for deployment.
• Collaborate with tooling, product, and training teams to improve usefulness and reliability of frontier models.
• Liaise with research and engineering teams to determine production-ready integrations for major releases.

Conocimientos

Post-training agentic workflows

Tool use integration

Distributed training on multi-node GPU

Multimodal models

Educación

MS/PhD preferred

Computer Science / ML background

Herramientas

GitHub

Hugging Face

Descripción del empleo

Tether is seeking an AI Research Engineer to advance agentic post-training, focusing on agent behaviors and tool invocation across edge devices. You will refine pre-trained models for reasoning, planning, and autonomous tool use, from mobile to server scale.

The role covers multimodal systems, distributed training, evaluation, and collaboration with cross-functional teams. You will publish in top AI venues and contribute open-source work.