Remote Agentic AI Engineer – Posttraining & Tooling

Nortal; La Pampa; Remote; ARS 216,357,000 - 309,081,000; Full time

Job summary

Tether is seeking an AI Research Engineer (Agentic Posttraining) to join its remote, globally distributed team. You will advance post-training methods to enhance agentic behaviors, enable tool use, and improve decision-making in edge devices and multi-modal systems.

You will work on integrating reasoning, planning, and tool invocation in large language models, with an emphasis on robust, goal-directed performance across diverse environments.

Qualifications

• Experience with large language model architectures and post-training for agentic workflows.
• Experience in tool use fine tuning, function calling, and RLHF for multi-turn tasks.
• Ability to curate agentic training data (trajectories, reasoning chains, environment interactions).
• Familiarity with building resource-efficient and/or multi-modal AI systems.

Responsibilities

• Drive innovation in post-training methodologies focused on agentic behaviors and tool use.
• Develop and test post-training algorithms enabling goal-directed behavior and reliable tool invocation.
• Curate training datasets (trajectories, tool use, reasoning chains) to strengthen baseline performance.
• Identify bottlenecks and implement improvements across agentic AI systems.

Skills

LLM architectures

Agentic post-training

Tool use fine-tuning

Reinforcement learning from feedback

Multi-modal models

Job description

Tether is seeking an AI Research Engineer (Agentic Posttraining) to join its remote, globally distributed team. You will advance post-training methods to enhance agentic behaviors, enable tool use, and improve decision-making in edge devices and multi-modal systems.

You will work on integrating reasoning, planning, and tool invocation in large language models, with an emphasis on robust, goal-directed performance across diverse environments.