Remote Agentic AI Scientist — Post-Training & Tooling

Alignerr Corp.; Rosario; Remote; ARS 184,482,000 - 276,723,000; Full time

Job summary

Tether is seeking an AI Research Engineer focused on post-training for agentic workflows, refining pre-trained models to reason, plan, and autonomously invoke external tools on edge devices. You will work on systems ranging from lean agents to multi-modal architectures, optimized for tool augmented decision making.

You will apply large language model expertise and post-training techniques to achieve SOTA results, including function calling, RL from feedback, and data-curation for tool use

Qualifications

• Degree in Computer Science, Machine Learning, or a related field; advanced degree (MS/PhD) preferred.
• Strong publication record in AI conferences is a plus.
• Experience with post-training workflows and tool use is desirable.

Responsibilities

• Conduct end-to-end research and engineering initiatives to advance post-training of agentic and tool-use models to achieve SOTA results.
• Drive broad, cross-cutting model improvements, including factuality, instruction adherence, tool/function use, multi-agent coordination, and reasoning calibration.
• 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 to assess model readiness for deployment.
• Strengthen feedback loops from real-world product usage, incorporating explicit and implicit user signals into post-training.
• Collaborate with tooling, product, and training teams to improve the usefulness, reliability, and agentic capabilities of frontier models.
• Closely liaise with research, engineering and cross-functional teams to determine integrations for production-ready model releases.

Skills

Deep learning

Reinforcement learning

Multimodal models

Education

PhD preferred in CS/ML

Job description

Tether is seeking an AI Research Engineer focused on post-training for agentic workflows, refining pre-trained models to reason, plan, and autonomously invoke external tools on edge devices. You will work on systems ranging from lean agents to multi-modal architectures, optimized for tool augmented decision making.

You will apply large language model expertise and post-training techniques to achieve SOTA results, including function calling, RL from feedback, and data-curation for tool use