Senior Software Engineer, Gemini Audio Inference - Mountain View
DeepMind
Job Description
About the Role
Our team is responsible for building the Productionization and Serving infrastructure for Gemini Audio Inference at Google DeepMind. We help land Gemini Audio capabilities into numerous clients including Astra, GeminiApp, YouTube, Search, Meet, Cloud, Geo, Assistant etc. Based on research Gemini model flavors, our tasks involve model latency/throughput optimizations, serializations, orchestration, evaluation & finally landing in production, at Google scale. Our team focuses deeply on Inference efficiencies for Gemini and its related components. We actively develop new infrastructure to make Gemini more accessible to new streaming use cases. Our team has deep collaboration with both the research team and production platform team, exposed with SOTA research work and their inference optimizations. Our team owns the infra to serve the Audio tokenization & Audio generation around the Gemini models. Join us if you are interested in having a direct impact on making Google's products better for our users in over 100 languages! Here are showcase videos that directly used the infra built from our team: Gemini Audio, Project Astra, Real Time Translation.
Key Responsibilities
- Work with research teams to build the serving solution of Gemini models for different clients.
- Propose and test the best serving configurations based on client needs.
- Build new infrastructure to serve Gemini in different ways, such as streaming.
- Design and build audio-specific logic in the orchestration framework.
- Ensure the Gemini model quality in the production environment.
- Build and improve infrastructure to support streaming Gemini prompts at large scale.
- Bring Gemini Audio related capabilities to clients, e.g., Long Context capabilities to Meet and YouTube clients; Audio Out capabilities to Maps team.
- Embrace a new orchestration infrastructure around Gemini model servings.
Requirements
- BS, MS or PhD degree in computer science, mathematics, applied stats, machine learning or similar experience working in industry.
- Experience working on software engineering projects from proof-of-concept through to implementation.
- Required programming languages: C++; Python a plus.
- Experience in performance engineering; GPU/TPU experience a plus.
- Great communication skills and interpersonal skills.
- Knowledge of machine learning and inference.
- Experience productionizing state-of-the-art large language and multimodal models a plus.
Nice to Have
- Python programming language skills.
- Experience with GPU/TPU hardware.
- Experience in performance engineering.
- Experience in productionizing large language and multimodal models.
Qualifications
- BS, MS or PhD degree in relevant fields.
Benefits & Perks
- US base salary range between $166,000 - $244,000 plus bonus, equity, and benefits.
Working at DeepMind
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.
Job Details
Job Skills
Key skills identified from this job posting
Sign upto access all insights for this job
About DeepMind
Website
deepmind.com
Company Size
1001-5000 employees
Location
Mountain View, CA
Industry
Software Publishers
Similar Jobs
Other opportunities you might be interested in
Software Engineer
Actalent
Senior Software Engineer, AI/ML, Ads Bidding Optimization
Software Engineer - Developer (Associate or Experienced)
Boeing
Python, AI Developer
Infosys
Software Development Engineer
Adobe
Software Development Engineer
Adobe