Agentic AI Post-Training Engineer — SOTA & Tooling

Alignerr Corp.; La Pampa; Remote; ARS 185,819,000 - 294,213,000; Full time

Job summary

Tether is hiring an AI Research Engineer (Agentic Post-training) for 100% remote worldwide work. You will push the boundaries of post-training for agentic systems, enabling tools use, reasoning, planning, and autonomous tool invocation on edge devices.

The role spans multimodal data, with models that reason, plan, and operate across diverse modalities. You will contribute to post-training at scale using distributed GPU frameworks, improve model capabilities, and publish results in leading AI

Qualifications

• Deep expertise in large language model architectures.
• Experience with post-training for agentic workflows.
• Hands-on experience with tool use fine tuning and function calling.
• Reinforcement learning from feedback on multi-turn interactions.

Responsibilities

• Conduct end-to-end research and engineering to advance post-training of agentic and tool-use models.
• Drive broad model improvements including factuality, instruction adherence, tool use, and multi-agent coordination.
• Design and enhance large-scale post-training systems, including data pipelines, training workflows, evaluation frameworks, and benchmark infrastructure.
• Develop rigorous evaluation suites and diagnostic tools for model readiness.
• Strengthen feedback loops from real-world product usage into post-training.
• Collaborate with tooling, product, and training teams to improve frontier models' usefulness and reliability.
• Liaise with research and engineering teams to determine production-readiness for major model releases.

Skills

LLM architectures

Agentic post-training

Tool use & function calling

Reinforcement learning from feedback

Education

Degree in Computer Science / ML or related field

Tools

Distributed training

Data pipelines

Job description

Tether is hiring an AI Research Engineer (Agentic Post-training) for 100% remote worldwide work. You will push the boundaries of post-training for agentic systems, enabling tools use, reasoning, planning, and autonomous tool invocation on edge devices.

The role spans multimodal data, with models that reason, plan, and operate across diverse modalities. You will contribute to post-training at scale using distributed GPU frameworks, improve model capabilities, and publish results in leading AI