LLM Platform Engineer, Gemini App Skills

Google LLC; Mountain View (CA); Presencial; USD 174.000 - 252.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Equity

Bonus target

Benefits

Descripción de la vacante

Google LLC's DeepMind seeks a Software Engineer for the Gemini App Skills Platform to drive the next generation of agentic AI. You will help transform Gemini from a conversational assistant into an action-oriented universal agent, architecting systems for discovery, retrieval, and execution of modular skills across Google, DeepMind, and partner ecosystems.

You will work with production serving in C++ and Python evaluation pipelines, interfacing with Research, Product, and Platform teams to push

Formación

• Experience developing software with large language models, agentic workflows, tool use, or retrieval-augmented generation (RAG).
• Experience designing evaluation datasets, automated rating systems, or conducting error analysis and prompt optimization for generative models.

Responsabilidades

• Design and build skill discovery, routing, and low-latency C++ serving components for Gemini across web, mobile, and Chrome.
• Pioneer dynamic system instructions, prompt representations, and semantic retrieval schemas for scaling skill catalogs.
• Design automated evaluation frameworks (auto-raters, simulators, benchmarks) to measure triggering precision, tool use, and parameter validity.
• Perform loss analysis on production telemetry, improve prompts/models to meet quality thresholds, and set reliability standards across the org.
• Collaborate with DeepMind Research, Search, Vertical teams and external engineers to onboard new modular capabilities.

Conocimientos

LLM development

Agentic workflows

Tool use

RAG integration

Evaluation design

Prompt optimization

Error analysis

Herramientas

C++

Python

Descripción del empleo

Google LLC's DeepMind seeks a Software Engineer for the Gemini App Skills Platform to drive the next generation of agentic AI. You will help transform Gemini from a conversational assistant into an action-oriented universal agent, architecting systems for discovery, retrieval, and execution of modular skills across Google, DeepMind, and partner ecosystems.

You will work with production serving in C++ and Python evaluation pipelines, interfacing with Research, Product, and Platform teams to push