Description
At Microsoft AI, we're on a mission to develop the most advanced algorithms for post-training large language models (LLMs) and deploy them to millions of users daily.
The model training team at Microsoft AI handles all aspects of post-training and improving pre-trained models to advance the state-of-the-art in various internal and external benchmarks. We're focused on enhancing model capabilities in areas such as coding, reasoning, instruction following, math, and agentic tasks.
As a Member of Technical Staff - Post Training, you'll contribute to all stages of the training process, including data collection and acquisition, building model capability evaluations, and applying advanced reward modeling and reinforcement learning techniques to develop and improve post-training recipes.
Responsibilities
- Develop data collection, evaluation, and post-training methods for models.
- Design hypotheses and experiment plans to rapidly iterate on model performance.
Qualifications
- Bachelor's degree in Computer Science, Machine Learning, Mathematics, or a related technical discipline, and 4+ years of technical engineering experience with coding in languages like C, C++, C#, Java, JavaScript, or Python.
- Experience with reward modeling, reinforcement learning, or other post-training techniques.
Preferred Qualifications
- Demonstrated experience in large-scale AI.
- Passion for conversational AI and its deployment.
- Strong written and verbal communication skills, with the ability to work closely with cross-functional teams.
- A passion for learning new technologies and staying updated with industry trends and best practices in AI.
- Proven ability to collaborate and contribute to a positive, inclusive work environment.
The typical base pay range for this role is $119,800 - $234,700 per year, depending on location.