Remote Senior AI Research Engineer – Agentic Posttraining

New Reach Education; Tandil; Remote; ARS 185,448,000 - 278,173,000; Full time

Job summary

Tether in a 100% remote worldwide role seeks an AI Research Engineer focused on post-training methods for agentic AI. You will refine pre-trained models to reason, plan, and autonomously invoke external tools on edge devices, driving robust, edge-optimized solutions.

Work spans streamlined agents to complex multi-modal architectures, all optimized for tool-augmented decision making. Deep expertise in LLMs and post-training for agentic workflows is essential, including RLHF and function calling.

Qualifications

• Expertise in large language model architectures.
• Experience with post-training for agentic workflows.
• Familiarity with tool use fine tuning and RLHF.

Responsibilities

• Develop post-training approaches for agentic behaviors.
• Design and evaluate tool invocation and planning.
• Curate agentic training data and analyze bottlenecks.

Job description

Tether in a 100% remote worldwide role seeks an AI Research Engineer focused on post-training methods for agentic AI. You will refine pre-trained models to reason, plan, and autonomously invoke external tools on edge devices, driving robust, edge-optimized solutions.

Work spans streamlined agents to complex multi-modal architectures, all optimized for tool-augmented decision making. Deep expertise in LLMs and post-training for agentic workflows is essential, including RLHF and function calling.