Remote AI Research Engineer: Agentic Post-Training

Mindrift; Ciudad de Mendoza; A distancia; ARS 185.448.000 - 293.627.000; Jornada completa

Descripción de la vacante

Tether is seeking an AI Research Engineer (Agentic Post-training) to advance post-training methodologies focused on agentic behaviors and tool use. You will refine pre-trained models to reason, plan, and autonomously invoke external tools for real-world, multi-step tasks on edge devices.

You will design scalable post-training systems, data pipelines, evaluation suites, and publish results at AI conferences, while contributing to open-source projects and cross-functional collaborations.

Formación

• Degree in Computer Science, ML, or related field
• MS/PhD preferred with publications in AI conferences
• Experience with multimodal post-training workflows and data pipelines
• Hands-on experience applying post-training at scale with distributed training

Responsabilidades

• Conduct end-to-end research and engineering initiatives to advance post-training of agentic and tool-use models
• Drive broad model improvements including factuality and tool use
• Design and enhance post-training systems, data pipelines, and evaluation frameworks
• Develop evaluation suites and diagnostics for model readiness
• Collaborate with tooling, product, and training teams to improve agentic capabilities
• Liaise with research and engineering teams to determine production-ready integrations

Descripción del empleo

Tether is seeking an AI Research Engineer (Agentic Post-training) to advance post-training methodologies focused on agentic behaviors and tool use. You will refine pre-trained models to reason, plan, and autonomously invoke external tools for real-world, multi-step tasks on edge devices.

You will design scalable post-training systems, data pipelines, evaluation suites, and publish results at AI conferences, while contributing to open-source projects and cross-functional collaborations.