Remote AI Agentic Designer & Tooling Evaluator

Yo Ai Labs; Rosario; Remote; ARS 212,695,000 - 334,235,000; Full time

Job summary

Tether is seeking an AI Research Engineer (Agentic Post-training) for a 100% remote worldwide role. You will join the AI model team to push post-training methodologies, enabling agentic behavior and autonomous tool use across edge devices and multi-modal inputs.

You will refine pre-trained models to reason, plan, and invoke external tools, with emphasis on scalability, evaluation, and real-world deployment readiness.

Qualifications

• Deep expertise in large language model architectures and post-training for agentic workflows.
• Experience with tool use fine tuning, function calling, and RLHF on multi-turn interactions.
• Strong publication record in AI conferences preferred.

Responsibilities

• Conduct end-to-end research and engineering initiatives to advance post-training of agentic and tool-use models.
• Drive cross-cutting model improvements including factuality, instruction adherence, tool use and multi-agent coordination.
• Design and optimize post-training systems, data pipelines, training workflows, and evaluation frameworks.
• Develop robust evaluation suites and diagnostic tools for deployment readiness.
• Collaborate with product and research teams to integrate production-ready models.

Skills

LLM architectures

Agentic workflows

Tool use fine tuning

Function calling

Reinforcement learning from feedback

Multimodal data handling

Education

Degree in Computer Science or Machine Learning

MS/PhD preferred

Tools

GitHub

Hugging Face

Distributed training frameworks

Job description

Tether is seeking an AI Research Engineer (Agentic Post-training) for a 100% remote worldwide role. You will join the AI model team to push post-training methodologies, enabling agentic behavior and autonomous tool use across edge devices and multi-modal inputs.

You will refine pre-trained models to reason, plan, and invoke external tools, with emphasis on scalability, evaluation, and real-world deployment readiness.