Senior Software Engineer (Machine Learning & Infrastructure), Acrobat AI Assistant

Our Company

Changing the world through digital experiences is what Adobe’s all about. We give everyone—from emerging artists to global brands—everything they need to design and deliver exceptional digital experiences! We’re passionate about empowering people to create beautiful and powerful images, videos, and apps, and transform how companies interact with customers across every screen.

We’re on a mission to hire the very best and are committed to creating exceptional employee experiences where everyone is respected and has access to equal opportunity. We realize that new ideas can come from everywhere in the organization, and we know the next big idea could be yours!

The Opportunity:

Adobe Document Cloud's AI team is looking for a Senior Software Engineer to improve our upcoming features. Our platform handles billions of PDFs and millions of transactions each month. Join our core team responsible for managing the central repository that supports all feature development and backend services for the Acrobat AI Assistant. This role plays a key role in facilitating fast feature development and building reliable components that are used extensively every day to serve our customers. We support features like question-answering (QA), suggested and related questions, attributions, document summaries, and more.

Our latest public features include Liquid Mode for PDFs on phones and tablets, PDF Extract API for unlocking PDF structure and content, Table Decomposition in Liquid Mode, and new generative AI features. All products use AI and are available on mobile, cloud, and desktop.

What You’ll Do:

• Design, build, and maintain scalable and efficient code solutions for the Acrobat AI Assistant.
• Develop and review specifications for safe client-service contracts, ensuring clear, concise, and secure interactions.
• Apply standard methodologies in code layering and modular design to ensure the development of robust and easily maintainable codebases.
• Conduct detailed reviews of pull requests and debug complex service integration issues.
• Lead the coordination and execution of service releases, ensuring they meet rigorous production standards.
• Work closely with feature teams to facilitate effective communication and knowledge sharing.
• Accelerate engineering productivity by empowering your fellow engineers with excellent tooling and systems.
• Build and provide operational support for globally deployed systems, powering some of the most advanced products in the market.

What You’ll Need to Succeed:

• B.S., M.Sc., or Ph.D. in Computer Science or equivalent practical experience with 5+ years of experience.
• Extensive software development experience, specifically in backend infrastructure, emphasizing code organization and architectural standard methodologies.
• Proficiency in designing and implementing concurrent and asynchronous systems using languages such as Python, JavaScript (Node.js), or Go.
• Familiarity with integrating language models within a feature pipeline.
• Strong understanding of event-driven architectures and non-blocking I/O operations.
• Understanding of OOP principles such as encapsulation, inheritance, polymorphism, and abstraction.
• Familiarity with common design patterns (e.g., Singleton, Factory, Observer, Strategy).
• Proficiency in writing unit and integration tests for object-oriented systems. Strong debugging skills.
• Proficiency in Python, with the ability to write clean, unit-tested, and well-documented code using docstrings. Familiarity with frameworks such as LangChain and Pydantic is highly desirable.
• Familiarity with prompt engineering, vector search techniques, and similar AI/ML technologies.
• Experience or willingness to learn how to create and review specifications for client-service contracts.
• Strong interpersonal skills with the ability to lead, mentor, and work collaboratively in a fast-paced environment.
• A proactive approach to identifying and resolving technical challenges independently.
• Flexibility in high-pressure settings.

Nice to Have:

• Experience in developing and deploying machine learning models in production environments.
• Expertise in continuous integration/continuous deployment pipelines, particularly in cloud environments.
• Experience with building and maintaining large-scale data processing systems, with a strong understanding of technologies like Kafka and Spark.
• Familiarity with networking protocols and monitoring systems, as well as experience in developing and maintaining RESTful APIs.

Inclusivity Statement: We are committed to building an inclusive and diverse work environment. We strongly encourage individuals from under-resourced groups, people of color, individuals with disabilities, and veterans to apply. We believe that a diverse range of perspectives and backgrounds strengthens our team, and we welcome all candidates who embody our values of collaboration, innovation, and respect.