Senior AI Research Engineer — Agentic Post-Training (Remote)

Alignerr Corp.; La Pampa; A distancia; ARS 184.482.000 - 276.723.000; Jornada completa

Descripción de la vacante

Tether is seeking an AI Research Engineer focused on agentic post-training, tool use, and multi-modal system integration. You will refine pre-trained models to reason, plan, and autonomously invoke external tools across edge devices, from phones to lightweight devices, while advancing safety and reliability.

You will work on large language models, tool use fine tuning, and reinforcement learning from feedback to push frontier AI capabilities.

Formación

• Requires advanced degree in CS/ML or equivalent research experience.

Responsabilidades

• Advance post-training of agentic and tool-use models for SOTA results.
• Improve factuality, instruction adherence, and tool use in models.
• Design data pipelines, training workflows, and evaluation frameworks.
• Develop diagnostics to assess model readiness for deployment.
• Collaborate with cross-functional teams to productionize integrations.

Conocimientos

LLM architectures

Agentic workflows

Tool use

Reinforcement learning

Research experience

Educación

MS/PhD in CS or ML

Herramientas

Distributed training frameworks

GitHub/Hugging Face

Descripción del empleo

Tether is seeking an AI Research Engineer focused on agentic post-training, tool use, and multi-modal system integration. You will refine pre-trained models to reason, plan, and autonomously invoke external tools across edge devices, from phones to lightweight devices, while advancing safety and reliability.

You will work on large language models, tool use fine tuning, and reinforcement learning from feedback to push frontier AI capabilities.