Software Engineer, Agentic Model Serving, Robotics
Confirmed on the employer's own hiring board on Nov 11, 2026. First seen by Alion on Nov 11, 2026.
About the job
Google's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information and one another. Our products need to handle information at massive scale, and extend well beyond web search. We're looking for engineers who bring fresh ideas from all areas, including information retrieval, distributed computing, large-scale system design, networking and data storage, security, artificial intelligence, natural language processing, UI design and mobile; the list goes on and is growing every day. As a software engineer, you will work on a specific project critical to Google’s needs with opportunities to switch teams and projects as you and our fast-paced business grow and evolve. We need our engineers to be versatile, display leadership qualities and be enthusiastic to take on new problems across the full-stack as we continue to push technology forward.
With your technical expertise you will manage project priorities, deadlines, and deliverables. You will design, develop, test, deploy, maintain, and enhance software solutions.
As a Software Engineer focusing on agentic robotics systems and model serving, you will bridge the gap between cutting-edge AI research and robust production systems by architecting and optimizing the full runtime stack-from on-robot harnesses and real-time control interfaces to edge and cloud serving infrastructure. You will build reliable, low-latency, and scalable solutions for real-world robotics applications, accelerating research initiatives and industry partnerships.
You will thrive at the intersection of machine learning infrastructure, distributed systems, and robotics, managing complex end-to-end challenges from co-designing on-robot execution and bidirectional streaming pipelines to optimizing and scaling foundation model inference across edge and cloud accelerators.
Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.
We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.US: $174000 - $252000 (USD) + 15% bonus target + equity + benefits
Learn more about benefits at Google.
Responsibilities
- Architect highly reliable and scalable full-stack model serving and deployment solutions spanning on-robot runtimes, local edge compute, and cloud backend systems (such as Beyond and Uniserve) customizing for stateful bidirectional streaming, multi-rate agentic control loops, and fast model hot-swapping in real-world robotics deployments.
- Conduct end-to-end performance analysis, profiling, and optimization across the entire sensory-to-action loop, from on-robot sensor ingestion, transport, and real-time execution handoffs to KV-cache management, graph compilation, and accelerator inference for cutting-edge robotics foundation models.
- Partner closely with research scientists, hardware/control engineers, and organizational partner teams to co-design agentic harnesses, streaming APIs, and closed-loop deployment workflows that provide flexibility and reliability across various robotics applications.
Qualifications
Minimum qualifications:
- 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 (e.g., TPUs and GPUs).
- Experience with machine learning frameworks, particularly JAX or TensorFlow, on inference and serving.
Preferred qualifications:
- Experience developing and integrating Google’s production model serving solutions like 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 to production deployment.
- Strong, proven programming skills in Python and C++.