Senior AI Engineer - Agentic Posttraining & Tool Use Remote

Fullstack; Tandil; Remote; ARS 139,086,000 - 231,811,000; Full time

Job summary

Tether is seeking an AI Research Engineer (Agentic Posttraining) to join our global, 100% remote team. You will advance post-training methods that help agents reason, plan, and autonomously invoke external tools to solve real-world tasks on edge devices such as smartphones.

The role emphasizes scalable, efficient architectures and strict attention to model safety and reliability. You will work on a spectrum from lightweight, resource-efficient agents to multi-modal systems that integrate text,

Qualifications

• Deep expertise in large language model architectures.
• Experience with post-training for agentic workflows and tool use.
• Proficiency in reinforcement learning from feedback on multi-turn interactions.
• Hands-on, research-driven approach to developing new post-training algorithms.

Responsibilities

• Curate agentic training data, including tool-use trajectories and reasoning chains.
• Identify bottlenecks and improve post-training for tool-augmented agents.
• Develop, test, and implement post-training algorithms for goal-directed behavior.
• Collaborate with cross-functional teams to deploy models on edge devices.

Job description

Tether is seeking an AI Research Engineer (Agentic Posttraining) to join our global, 100% remote team. You will advance post-training methods that help agents reason, plan, and autonomously invoke external tools to solve real-world tasks on edge devices such as smartphones.

The role emphasizes scalable, efficient architectures and strict attention to model safety and reliability. You will work on a spectrum from lightweight, resource-efficient agents to multi-modal systems that integrate text,