Senior AI-First Engineer - Agentic Tools (Remote)

Homie.Mx; Tandil; Remote; ARS 200,903,000 - 293,627,000; Full time

Job summary

Tether is seeking an AI Research Engineer (Agentic Posttraining) to join the AI model team. You will advance post-training methods for agentic behaviors, focusing on tool use and external calls to solve complex tasks on edge devices.

You will work on scalable, resource-conscious agents, combining text, images, and audio, with a hands-on, research-driven approach to develop new post-training algorithms that enable goal-directed behavior and robust tool invocation.

Qualifications

• Deep expertise in large language model architectures.
• Experience in post-training for agentic workflows, including tool use fine tuning, function calling, and RL from feedback on multi-turn interactions.
• Hands-on, research-driven approach to developing post-training algorithms that enable goal-directed behavior and reliable tool invocation.

Responsibilities

• Curate agentic training data (trajectories of tool use, reasoning chains, environment interactions).
• Strengthen baseline performance and identify bottlenecks in post-training for tool augmented agents.

Skills

Agentic AI

LLM expertise

Post-training

Tool use

Edge devices

Tools

Python

PyTorch

ML tooling

Job description

Tether is seeking an AI Research Engineer (Agentic Posttraining) to join the AI model team. You will advance post-training methods for agentic behaviors, focusing on tool use and external calls to solve complex tasks on edge devices.

You will work on scalable, resource-conscious agents, combining text, images, and audio, with a hands-on, research-driven approach to develop new post-training algorithms that enable goal-directed behavior and robust tool invocation.