AI Agentic Post-Training Engineer (Remote)

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

Job summary

Tether is hiring an AI Research Engineer (Agentic Posttraining) for a fully remote role available worldwide. You will advance agentic AI through post-training methods, focusing on tool use, planning, and autonomous decision making.

The role spans edge devices and diverse hardware, with a strong emphasis on reliability and scalability. You will drive data curation for agentic training, implement new post-training algorithms, and collaborate across teams to push the frontier of agentic AI in

Qualifications

• Experience with post-training workflows for agentic AI
• Strong understanding of large language model architectures and tool use
• Experience in reinforcement learning from feedback (RLHF)

Responsibilities

• Curate agentic training data and tool-use trajectories
• Develop post-training algorithms to enhance agentic behavior
• Test and implement new post-training approaches for tool augmentation
• Collaborate with research and engineering teams to deploy models

Skills

Agentic posttraining

Tool use

LLM architectures

Reinforcement learning

Tools

Python

PyTorch

Job description

Tether is hiring an AI Research Engineer (Agentic Posttraining) for a fully remote role available worldwide. You will advance agentic AI through post-training methods, focusing on tool use, planning, and autonomous decision making.

The role spans edge devices and diverse hardware, with a strong emphasis on reliability and scalability. You will drive data curation for agentic training, implement new post-training algorithms, and collaborate across teams to push the frontier of agentic AI in