Microsoft PRINCIPAL APPLIED SCIENTIST 

Taiwan, Taoyuan City 

392014470

have a challenge– theyneed the tools to build agentic experiences overpublic and private knowledge.leading thedeliver the next chapter ofRAG (retrieval-augmented generation)that cantogether many sources of data andtransform data into knowledge., Azure’sretrieval platformmeet the demands of complexqueries that require reasoning and reflecto deliver high quality results.span manyindustries, corpus sizes and scenarios, and our work includes multiple aspects,such as:

• LLMprompts,agentsandquery executionworkflows,often with tight latency constraints

• Collection, generation and filtering of training and evaluation data

• Building offstate of the arttechniques

You canfollow ourprogression from better search, to RAG

major aspect of this role is to pushr development of knowledge retrieval to the frontier. This requires a capableindividual whois well verseth deep learningand LLM– someone who cansolve the hardest challenges wherethe latest reasoning modelare bestlow latencyoptions wherespeed is critical.

Required/minimum qualifications

• Bachelor's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years related experience (e.g., statistics, predictive analytics, research)
  • OR Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 4+ years related experience (e.g., statistics, predictive analytics, research)
  • OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 3+ years related experience (e.g., statistics, predictive analytics, research)
  • OR equivalent experience.

1. ’applied science strategy, incorporatingstate of the artresearchintotechniquesshipped to production
2. Select,developand build metrics to use across the full range of search engine components;
3. Seek out and incorporate customer feedback intodataset construction,evaluationsandtechniquedevelopment;
4. Provide technical leadership and contribute to experimentation infrastructure and proofs-of-concept to test outnew ideasand concepts;
5. Advances thequalityof theteamsexperimentalcodebase to ensure experiments are efficient and repeatable;
6. Nurtures and grow multiple collaborative relationshipswith program management, engineers, and other functions across products;
7. Sets the bar for how the team plans,documentsand communicatesin a clear and efficient way.