Senior Research Engineer, Post-Training & Model Alignment (AI Safety)

techify • Switzerland

Visa Sponsorship

Apply Now

AI Summary

Lead the development and optimization of post-training techniques for Anthropic’s frontier AI models, bridging cutting-edge research and production engineering. Implement scalable alignment methodologies like RLHF and Constitutional AI to enhance model safety, quality, and steerability. Collaborate across interdisciplinary teams to debug, refine, and deploy high-impact AI systems in a fast-paced, research-driven environment.

Key Highlights

Directly impact production model quality, safety, and capabilities through post-training optimization

Work at the intersection of research and engineering with on-call incident response requirements

All interviews conducted in Python; preference for senior engineers with frontier AI systems experience

Key Responsibilities

Implement and optimize post-training techniques (e.g., RLHF, Constitutional AI) at scale for frontier models

Design, build, and maintain robust pipelines for model fine-tuning and evaluation

Collaborate with research teams to translate emerging alignment techniques into production-ready systems

Debug complex training pipelines and model behavior, ensuring reliability and reproducibility

Develop tools to measure and improve model performance across safety, quality, and capability dimensions

Searching for Development & Programming roles that provide visa sponsorship? Connect with international employers through Development & Programming Jobs with Visa Sponsorship opportunities actively seeking talented professionals.

Technical Skills Required

Python Distributed Computing Large Language Model Training

Benefits & Perks

Competitive compensation

Generous vacation and parental leave

Flexible working hours

Explore our comprehensive directory of visa sponsorship jobs from employers worldwide who are ready to sponsor talented international professionals.

Nice to Have

Experience with LLMs (Large Language Models)

Interest in AI safety and responsible deployment

Background in physics, biology, or empirical AI research

Job Description

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.Anthropic's production models undergo sophisticated post-training processes to enhance their capabilities, alignment, and safety. As a Research Engineer on our Post-Training team, you'll train our base models through the complete post-training stack to deliver the production Claude models that users interact with.

Want the full job description? Read the complete details on LinkedIn, the original posting.

Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.