Principal Applied Scientist

Microsoft•Redmond, WA

About The Position

We are seeking a highly motivated and technically skilled Applied Data Scientist to join the PAX team, driving innovation at the intersection of organizational intelligence, Generative AI, and Bizchat integration. This role will replace Qiang Gan and focus on building and evaluating intelligent experiences that empower users to query and understand organizational data through conversational interfaces. You will lead efforts in prompt engineering, SEVAL (Semantic Evaluation), and Bizchat integration, collaborating across engineering, product, and research teams to deliver high-quality, scalable AI solutions. Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

Requirements

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.
Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include but are not limited to the following specialized security screenings:
Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud background check upon hire/transfer and every two years thereafter.

Nice To Haves

Experience with SEVAL or similar semantic evaluation systems.
Prior work on conversational AI, NLP, or organizational analytics.
Proven ability to work cross-functionally in fast-paced, ambiguous environments.
Solid communication skills and ability to influence across teams.
7+ years of experience in applied data science, machine learning, or AI product development.
Solid proficiency in ML frameworks.
Hands-on experience with LLMs, prompt engineering, and agentic workflows.
Experience with evaluation frameworks and metrics-driven experimentation.
Familiarity with Microsoft stack: Azure ML, Copilot Studio, Power Platform, and Bizchat APIs.

Responsibilities

Bizchat Integration
Architect and implement data pipelines and APIs that connect PAX organizational datasets to Bizchat and Copilot experiences.
Collaborate with platform teams to ensure seamless integration of PAX plugins and reasoning models into Bizchat workflows.
Drive experimentation and tuning of Bizchat responses using PAX data, ensuring high answer rates and relevance across public and private attributes.
Prompt Engineering
Design, test, and optimize prompts for LLM-powered agents and tools within Bizchat and Copilot Studio.
Develop multi-turn conversational flows and agentic reasoning chains to support complex organizational queries.
Collaborate with product and UX teams to refine prompt strategies for clarity, safety, and user satisfaction.
SEVAL & Evaluation Frameworks
Build and maintain SEVAL pipelines to evaluate grounding, factuality, latency, and cost of AI responses.
Lead efforts to expand SEVAL coverage for cross-org queries, dynamic attributes, and custom columns.
Partner with engineering to implement telemetry and feedback loops for continuous model improvement