Microsoft Senior Research Engineer 

United States, Washington 

957157273

Research Engineer

As aResearch Engineer, you will play a crucial role in advancing the frontier of constrained decoding and imagining new application programming interface (APIs) for language models. Ifexcited about links between formal grammars and generative AI, deeply understanding andLLM inference, enabling more responsible AI without finetuning and RLHF, and/or exploring fundamental changes to the “text-in, text-out” API,, multidisciplinary research.

Required Qualifications:

• Bachelor's Degree in Computer Scienceor related technical field AND 4+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python
  • OR equivalent experience

Preferred Qualifications:

• Bachelor's Degree in Computer Science, or related technical discipline AND8+ years technical engineering experience with coding in languages including, but not limited to, Python, C, C++, Rust, or C#
  • ORMaster's Degree in Computer Scienceor related technical field AND6+ years technical engineering experience with coding in languages including, but not limited to, Python, C, C++, Rust, or C#
  • OR equivalent experience
• Expertiseon one of the following preferred:
  • Deep familiarity with transformer-based model inference, including batch processing paradigms for hosted models
  • Expertisein context-free grammar specification and parsing
  • Experience with constrained decoding paradigms (regex-based constraints,grammar basedconstraints, JSON mode, function calling, etc.)
• Contribution history to open-source projects, especially in the LLM/AI space
• Familiarity with the research process anda publicationhistory in AI conferences
• Familiarity with Python programming paradigms and modern LLM APIs
• Effective communication skills and desire to collaborate in a multi-disciplinary team
• Familiarity with Guidance

Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here:Microsoft will accept applications for the role until August 13, 2024.

• Develop and implement new constrained decoding research techniques for increasing LLM inference quality and/or efficiency. Example areas of interest include speculative execution, new decoding strategies (e.g.extensions to beam search), “classifier in the loop” decoding for responsible AI, improving AI planning, and explorations of attention-masking based constraints.

• Re-imagine the use and construction of context-freegrammars(CFG) and beyond to fit Generative AI. Examples of improvements here include better tools for constructing formalgrammars, extensions to Earley parsing, and efficient batch processing for constrained generation. Consideration of how these techniquesarepresented to developers – who may not be well versed ingrammarsand constrained generation -- in an intuitive, idiomatic programming syntax is also top of mind.

• Design principled evaluation frameworks and benchmarks for measuring the effects of constrained decoding on a model. Some areas of interest to study carefully include efficiency (token throughput and latency), generation quality, and impacts of constrained decoding on AI safety.

• Publish your research in top AI conferences and contribute your research advances to the guidance open-source project.

• Embody our