Remote AI Agentic Post-Training Engineer

Alignerr Corp.; Tandil; Remote; ARS 227,887,000 - 349,427,000; Full time

Job summary

Tether is seeking an AI Research Engineer (Agentic Post-training) to advance post-training methods for agentic workflows and tool use. You will work on post-training for multi-modal models, aiming for robust, rule‑compliant behavior across edge devices and cloud environments.

You will contribute to data pipelines, evaluation frameworks, and deployment readiness, with a strong emphasis on reproducibility, scalability, and collaboration with cross-functional teams.

Qualifications

• Degree in Computer Science or Machine Learning; advanced degree preferred.
• Publications in top AI conferences encouraged.

Responsibilities

• Conduct end-to-end research and engineering initiatives to advance post-training of agentic and tool-use models to achieve SOTA results.
• Drive model improvements, including factuality, instruction adherence, tool 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 usefulness, reliability, and agentic capabilities of frontier models.
• Liaise with research and engineering teams to determine production readiness for major releases.

Skills

Agentic post-training

Tool use

Reinforcement learning from feedback

Multimodal systems

Distributed training

Education

MS/PhD in CS/ML

Publications in AI conferences

Tools

GitHub / Hugging Face

GPU clusters

Job description

Tether is seeking an AI Research Engineer (Agentic Post-training) to advance post-training methods for agentic workflows and tool use. You will work on post-training for multi-modal models, aiming for robust, rule‑compliant behavior across edge devices and cloud environments.

You will contribute to data pipelines, evaluation frameworks, and deployment readiness, with a strong emphasis on reproducibility, scalability, and collaboration with cross-functional teams.