AI Agentic Post-Training Engineer — SOTA & Tooling Expert

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

Job summary

Tether is hiring an AI Research Engineer focusing on post-training for agentic models. You will refine pre-trained models to reason, plan, and autonomously invoke external tools across edge devices, while advancing multimodal capabilities and robust tool use.

You will work on scalable post-training systems, data pipelines, and evaluation frameworks, collaborating with researchers and engineers to push state-of-the-art results in a distributed, remote environment.

Qualifications

• Deep expertise in large language model architectures and post-training for agentic workflows.
• Experience with tool use fine tuning, function calling, and RL from feedback on multi-turn interactions.
• Proven experience with multimodal post-training workflows and data pipelines.

Responsibilities

• Conduct end-to-end research and engineering initiatives to advance post-training of agentic and tool-use models to achieve SOTA results.
• Drive cross-cutting model improvements: factuality, instruction adherence, tool use, multi-agent coordination, reasoning calibration.
• Design and enhance large-scale post-training systems: data pipelines, training workflows, evaluation frameworks, benchmarks.
• 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.
• Collaborate with tooling, product, and training teams to improve usefulness and agentic capabilities.
• Liaise with research and engineering to determine production-ready integrations for major releases.
• Open to candidates with publications in top AI conferences and open-source contributions.

Skills

LLM architectures

Agentic post-training

Tool use fine-tuning

Function calling

RL from feedback

Multimodal workflows

Education

PhD or MS in related field

MS/PhD preferred

Tools

Distributed training frameworks

GPU clusters

Job description

Tether is hiring an AI Research Engineer focusing on post-training for agentic models. You will refine pre-trained models to reason, plan, and autonomously invoke external tools across edge devices, while advancing multimodal capabilities and robust tool use.

You will work on scalable post-training systems, data pipelines, and evaluation frameworks, collaborating with researchers and engineers to push state-of-the-art results in a distributed, remote environment.