19 oct
|
Alignerr
|
Neuquén
As a member of the AI model team, you will drive innovation in post-training methodologies, focusing on agentic behaviors and tool use. Your work will refine pre-trained models to enable reasoning, planning, and autonomous tool invocation on edge devices.
This role covers multimodal systems, from lightweight agents to complex architectures, and demands deep expertise in LLMs and post-training. You will curate training data, improve baselines, and push toward SOTA performance while collaborating
📌 Remote AI Agentic Training Engineer (Neuquén)
🏢 Alignerr
📍 Neuquén