Software Engineer, Agentic Model Serving, Robotics
Google DeepMind · Mountain View, CA, USA
Frontier labonsitemid-level$174k–$252k
At a glance
Highlights
- Architect scalable serving spanning on-robot runtimes, edge and cloud.
- Optimize end-to-end sensory-to-action loop for real-world robots.
- Co-design streaming harnesses for multi-rate agentic control loops.
What they offer
- 15% bonus target
- equity
- benefits
Ideal candidate
A versatile systems-minded engineer with production ML experience who loves bridging research and robust deployment to make real-world robots fast, reliable, and scalable.
Requirements
- Bachelor's degree or an advanced degree
- 4 years of experience in software development
- Experience working with LLMs or VLMs in a production environment
- Experience optimizing model performance for inference on hardware accelerators
- Experience with machine learning frameworks focused on inference and serving
- Experience developing and integrating production model serving solutions
- Experience integrating security best practices into ML infrastructure
- Familiarity with robotics software stacks and taking features to production deployment
- Strong programming skills in Python and C++
Lab profile
About Google DeepMind
Google's AI lab building frontier models like Gemini to advance science and general intelligence.
What they build
- Gemini
- Gemma
- AlphaFold
Known for
- Frontier foundation models and GenAI
- Large-scale training with JAX, PyTorch, TensorFlow
- Model evaluation and deployment expertise
- Responsible frontier AI research
Key facts
- Founded in 2010
- Headquartered in London, UK
- Part of Google (Alphabet)
First seen · Last seen