The Siri Natural Language Understanding (NLU) team needs to develop and extend Siri's NLU to enable understanding of complex, nuanced intents to support the growth of Siri's functionality and usefulness. This role will help improve the data quality and throughput of Siri NLU model development, ultimately delivering a better Siri virtual assistant to a global user base.
Requirements
- Experience designing, building, and maintaining APIs (GraphQL preferred), and cloud technologies (Kubernetes and AWS preferred).
- Proficient coding skills in the back-end, data manipulation, and scripting languages (e.g., Python, Swift, Golang)
- Proficient in SQL and NoSQL databases to build solutions for large scale systems (e.g., PostgresSQL, DynamoDB, Elasticsearch/OpenSearch &AWS Iceberg)
- Experience with web programming languages (e.g., Typescript/Javascript, NodeJS, CSS) and modern frontend/web library/framework (React, Redux, NextJS)
- Some experience in building highly available production services, including deployment automation and scaling
- Excellent grasp of the fundamentals of software engineering
- Proficient knowledge of Git
Responsibilities
- Conceptualize, design, develop, test, deploy, maintain and improve annotation tooling with a modern technology stack, continuous integration, and deployment that will be used by multiple teams within AI/ML
- Developing and maintaining complex, rich, large-scale web applications for data-intensive systems.
- Build APIs and UIs that are simple and powerful
- Help scale data infrastructure and drive data efficiency
- drive the design and implementation of the annotation tooling data pipeline and web services to support the development of next-generation NLU technologies
- working directly with NLU data scientists and modeling engineers to interpret requirements and make informed design decisions
- develop highly reliable and scalable web services, and APIs
Other
- Ability to clearly communicate, and collaborate with designers, front end engineers, annotation project leads, data scientists, and data engineers
- BS, MS in Computer Science, Computer Engineering, or equivalent degree with applicable experience
- Experience with large-scale distributed data processing (e.g., Hadoop, Spark, Kafka)
- Demonstrates experience architecting and integrating Large Language models into production grade full stack applications, data pipelines or agents workflows, utilizing APIs such as OpenAI, Anthropic Claude & HuggingFace for open source models
- Hands-on experience leveraging AI-assisted development environments and code generation tooling (e.g. Claude code, Cursor, GPT-based agent playgrounds) to accelerate prototyping, improve engineering velocity and enhance developer productivity
