Are you an Principal Software Engineer passionate about advancing AI technologies and making a tangible impact on both internal Microsoft and external products/applications? Join the Microsoft AI Platform team, where we specialize in delivering efficient runtime and end-to-end applications for state-of-the-art AI models. Our work powers a wide array of applications, from internal tools like co-pilots to third-party solutions, by providing scalable, cost-efficient inferencing for speech, vision, and text inputs.

As part of the Azure OpenAI Core team, our mission is to:

• Ship OpenAI Models with Agility: We bring cutting-edge AI models to production quickly and efficiently.

• Optimize Runtime for DNN Model Inferencing: We focus on enhancing the performance of deep neural network models.

• Support Multi-Modal Model Inferencing: Using techniques like batching and data/model parallelization, we manage diverse input types seamlessly.

We support a broad range of customers, from internal Microsoft teams to external clients, tackling tasks in Speech, Computer Vision, and Natural Language Processing (NLP). Our end-to-end approach involves optimizing inferencing traffic at web scale and fine-tuning model execution for various traffic patterns.

Why Join Us?

• Innovative Work Environment: Work on state-of-the-art models and run them in a cost-efficient way.

• Flexibility: Partner with your manager to define your work style, whether in-office or from home.

• Growth Opportunities: Engage in a range of projects, from distributed systems to DNN model inferencing and personalization.

What You’ll Do

• Collaborate: Work closely with runtime engines to optimize model execution and manage inferencing traffic at a web scale.

• Innovate: Engage in cutting-edge projects involving distributed computing and deep neural network model inferencing.

• Impact: Contribute to the development of scalable, efficient AI solutions that power applications worldwide.

If you’re excited about working with the latest AI technologies and contributing to impactful projects, we’d love to hear from you. Join us at Microsoft and help shape the future of AI.

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.

In alignment with our Microsoft values, we are committed to cultivating an inclusive work environment for all employees to positively impact our culture every day.

Responsibilities

Design and implement high performance microservice components, algorithms and integration with other services to deliver scalable API, offline containers as well as libraries for Microsoft Office and Azure Open AI services.

• Innovate and bring cutting edge solutions to run AI models at scale ranging from core runtime enhancement using batching, intelligent data packing, parameter efficient inferencing, orchestrating between different AI components.

• Trouble shoot system level live services, offline container performance across data centers

• Improve the quality of model inference by improving personalization algorithms and customer specific data.

• Implement telemetry and logging to monitor the health of the features continually and automatically.

Other:

• Embody our Culture (https://www.microsoft.com/en-us/about/corporate-values) and Values (https://careers.microsoft.com/us/en/culture)

Qualifications

* Required Qualifications:*

• Bachelor's Degree in Computer Science, or related technical discipline AND 6+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python o OR equivalent experience.

• 2+ years of experience in distributed computing OR distributed systems OR (AI & ML) OR speech OR Computer Vision OR NLP.

Other Requirements:

• 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.

Preferred Qualifications:

• Effective written and verbal communication skills

• Results-oriented free thinkers with ability to socialize and drive their ideas into the technology.

• Experience implementing high performance algorithms, with offloading to hardware accelerators OR GPU is a plus. 

Software Engineering IC5 - The typical base pay range for this role across the U.S. is USD $137,600 - $267,000 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $180,400 - $294,000 per year.

Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here:

https://careers.microsoft.com/us/en/us-corporate-pay

Microsoft will accept applications for the role until October 3, 2024.

#AIPlatform

Microsoft is an equal opportunity employer. Consistent with applicable law, 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 and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations (https://careers.microsoft.com/v2/global/en/accessibility.html) .