Software Engineer, Astra Exploratory Engineer

At Google DeepMind, we value diversity of experience, knowledge, backgrounds and perspectives and harness these qualities to create extraordinary impact. We are committed to equal employment opportunities regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law. If you have a disability or additional need that requires accommodation, please do not hesitate to let us know.

Snapshot

Our team is helping develop next-gen capabilities for Astra, GDM’s universal agent prototype. These capabilities include integration of Google services (Gmail, Calendar, etc.) as well as completely new agent experiences like homework tutors, city guides, and AskPhotos. 

About us

Artificial Intelligence could be one of humanity’s most useful inventions. At Google DeepMind, we’re a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence. We use our technologies for widespread public benefit and scientific discovery, and collaborate with others on critical challenges, ensuring safety and ethics are the highest priority.

The role

This role on the Astra Exploratory team is targeted toward the development of new state of the art capabilities for Google’s Astra Agent. SWEs in this role will develop on the core codebase and help onboard PA collaborators partnering with us to bring all of Google’s capabilities to Astra as a Universal Assistant.

Key responsibilities

This role will be central in supporting partners from across Google to use Astra as an Agent Platform for their services and experiences. In this role you will:

• Develop within the core Astra code base, contributing to server-side agent functionality, including prompting, tool use, and backend processing.
• Work directly with PA partners to identify opportunities to partner and architecting solutions for integration.
• Designing and implementing evaluation strategies comprising data set needs, component level eval, and agent-level end to end evaluation of new capabilities and experiences.
• Drive high-quality demos for major AI moments at Google (IO, Made By Google, etc.)

About you

Successful candidates will have a track record of fast prototyping work combined with production level engineering. Knowing how to define a problem from requirements based evaluation and executing in quick incremental and demo’able steps is required.

In order to set you up for success as an Astra Exploratory Engineer at Google DeepMind, we look for the following skills and experience:

• Bachelor's degree or equivalent practical experience.
• 8 years of experience in software development, and with data structures/algorithms.
• Exposure to Python for ML.
• Exposure to Python at Google and its usage patterns within g3.
• Exposure to C++ at Google and its usage patterns within g3.
• Designing complex software features, including evaluating alternatives, and performing short and long term trade-offs
• Implement high quality code, well tested and easy to maintain

In addition, the following would be an advantage: 

• Experience building AI Agent capabilities (Tools, Memory, Planning, etc.)
• Open source experience, e.g. making pull requests on Github.
• Experience with Generative AI Agents and their use cases.
• Development familiarity with industry-available generative AI APIs and libraries.  
• Python/C++ readability.
  
  

The US base salary range for this full-time position is between $189,000 - $300,000 + bonus + equity + benefits. Your recruiter can share more about the specific salary range for your targeted location during the hiring process.

Application deadline: 12pm GMT Thursday 14th Nov 2024 

Note: In the event your application is successful and an offer of employment is made to you, any offer of employment will be conditional on the results of a background check, performed by a third party acting on our behalf. For more information on how we handle your data, please see our Applicant and Candidate Privacy Policy.