Software Engineer, Agentic Model Serving, Robotics, DeepMind

Google•Mountain View, CA
•$174,000 - $252,000

About The Position

Google’s software engineers develop next-generation technologies that change how billions of users connect, explore, and interact with information. Engineers work on projects critical to Google’s needs and design, develop, test, deploy, maintain, and enhance software solutions while managing project priorities, deadlines, and deliverables. This role focuses on agentic robotics systems and model serving. It bridges AI research and production systems by architecting and optimizing the runtime stack, including on-robot harnesses, real-time control interfaces, and edge and cloud serving infrastructure. The work involves building reliable, low-latency, scalable solutions for robotics applications and supporting research initiatives and industry partnerships. The engineer will work across machine learning infrastructure, distributed systems, and robotics, addressing end-to-end challenges such as on-robot execution, bidirectional streaming pipelines, and foundation-model inference across edge and cloud accelerators. Google DeepMind’s teams advance AI development for global challenges and product innovation, with safety and ethics as priorities.

Requirements

  • Bachelor's degree or an advanced degree.
  • 4 years of experience in software development.
  • Experience working with Large Language Models (LLMs) or Vision-Language Models (VLMs) in a production environment.
  • Experience optimizing model performance for inference on hardware accelerators such as TPUs and GPUs.
  • Experience with machine learning frameworks, particularly JAX or TensorFlow, on inference and serving.

Nice To Haves

  • Experience developing and integrating Google’s production model-serving solutions, such as Beyond and Uniserve.
  • Experience integrating security best practices directly into ML infrastructure.
  • Expertise in building, profiling, and optimizing complex, highly available, and secure software systems for end-to-end performance.
  • Familiarity with robotics software stacks and demonstrated experience taking complex technical features from initial design through production deployment.
  • Strong, proven programming skills in Python and C++.

Responsibilities

  • Architect reliable and scalable full-stack model-serving and deployment solutions across on-robot runtimes, local edge compute, and cloud backend systems, customizing for stateful bidirectional streaming, multi-rate agentic control loops, and fast model hot-swapping in robotics deployments.
  • Analyze, profile, and optimize end-to-end performance across the sensory-to-action loop, including sensor ingestion, transport, real-time execution handoffs, KV-cache management, graph compilation, and accelerator inference.
  • Partner with research scientists, hardware and control engineers, and organizational partner teams to co-design agentic harnesses, streaming APIs, and closed-loop deployment workflows for robotics applications.
  • Manage project priorities, deadlines, and deliverables; design, develop, test, deploy, maintain, and enhance software solutions.

Benefits

  • 15% bonus target
  • Equity
  • Benefits
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service