Remote AI Agentic Systems Engineer

Yo Ai Labs; Rosario; A distancia; ARS 181.747.000 - 272.620.000; Jornada completa

Descripción de la vacante

Tether’s AI research team seeks an AI Research Engineer to advance post-training for agentic systems, focusing on tool use and autonomous reasoning across edge devices and scalable architectures.

You will craft end-to-end post-training workflows, curate datasets, and collaborate with engineering and product teams to push state-of-the-art capabilities while ensuring reliability and scalability.

Formación

• Deep expertise in large language model architectures.
• Experience with post-training for agentic workflows.
• Experience with tool use fine tuning and function calling.
• Strong publication record in AI conferences.
• Open-source contributions related to agentic systems.

Responsabilidades

• Conduct end-to-end research and engineering on post-training for agentic and tool-use models to achieve SOTA results.
• Drive broad model improvements: factuality, instruction adherence, tool use, multi-agent coordination, reasoning calibration.
• Design and enhance post-training systems: data pipelines, training workflows, evaluation frameworks, benchmark infrastructure.
• Develop rigorous evaluation suites and diagnostics for deployment readiness.
• Strengthen feedback loops from real-world usage and user signals into post-training.
• Collaborate with tooling, product, and training teams to improve agentic capabilities for major releases.

Conocimientos

LLM architectures

Agentic workflows

Tool use

Distributed training

Educación

Degree in computer science

MS/PhD preferred

Herramientas

GitHub

Hugging Face

Descripción del empleo

Tether’s AI research team seeks an AI Research Engineer to advance post-training for agentic systems, focusing on tool use and autonomous reasoning across edge devices and scalable architectures.

You will craft end-to-end post-training workflows, curate datasets, and collaborate with engineering and product teams to push state-of-the-art capabilities while ensuring reliability and scalability.