Principal Applied Scientist
Microsoft
Barcelona, Spain
Microsoft’s Enterprise customers have a challenge – they need the tools to build agentic experiences over public and private knowledge. The Azure AI Knowledge team is leading the way to deliver the next chapter of agentic retrieval through Foundry IQ Knowledge bases to bring together many sources of structured and unstructured enterprise data and transform it into knowledge. We are continuously developing and deploying new capabilities to meet the demands of complex queries that require reasoning and reflection to deliver high quality results. Our customers span many different industries, corpus sizes and scenarios, and our work includes multiple aspects, such as:
Developing LLM prompts, agents and query execution workflows, often with tight latency constraints
Collection, generation and filtering of training and evaluation data
Building off state of the art techniques from across Microsoft and the industry
Use of AI coding patterns to parallelize and accelerate experimentation
You can follow our progression from better search, to RAG, to agentic retrieval:
As a team, we leverage the diverse backgrounds and experiences of passionate engineers, scientists, and program managers to help us realize our mission to empower every person and every organization on the planet to achieve more. We believe great products are built by inclusive teams of customer-obsessed individuals who trust each other and work closely together. We collaborate regularly across the company with teams like M365, Bing and Microsoft Research.
A major aspect of this role is to push our development of knowledge retrieval to the frontier. This requires a capable individual who can leverage multiple coding agents to explore new techniques (autoresearch, claws, CLI systems, etc) and bring them to production at scale.
If you are passionate about working on the latest and hottest areas in Artificial Intelligence, Machine Learning, and data science, all the while making search better for customers across the world, then this is the team you’re looking for!
Responsibilities
- Lead state-of-the-art research incorporation into techniques shipped to production
- Proactively develop and build metrics to use across the full range of search engine components
- Seek out and incorporate customer feedback into dataset construction, evaluation, and technique development
- Lead technical excellence and contribute to experimentation infrastructure and proofs-of-concept using AI coding agents
- Advance the quality of the team’s experimental codebase to ensure experiments are efficient and repeatable
- Nurture collaborative relationships with product management, engineers, and other functions across products
- Drive clear and efficient plans, documentation, and communication
Qualifications
Required/minimum qualifications
- Bachelor's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 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 years related experience (e.g., statistics, predictive analytics, research)
- OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND years related experience (e.g., statistics, predictive analytics, research) OR equivalent experience.
Additional or preferred qualifications
- Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND years related experience (e.g., statistics, predictive analytics, research) OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND years related experience (e.g., statistics, predictive analytics, research) OR equivalent experience.
- Experience developing and deploying machine learning products or systems at multiple points in the product cycle from ideation to shipping.
- Experience with agentic coding systems, including scaffolding for long‑running agents.
- Strong hybrid collaboration skills, with clear async/sync communication and teamwork.
- Experience defining task‑specific metrics and evaluation datasets.
- Customer‑focused and execution‑driven, with strong ownership and bias for action.
- Strong problem‑solver, comfortable with novel, open‑ended problems.
#AIPLATFORM#
This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.
Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.