Staff Software Engineer, AAI Research
Google · Schweiz · Full time · Onsite
At a glance
Staff Software Engineer, AAI Research at Google, working with Python, Google Cloud and AI / Machine Learning.
- Location
- Schweiz
- Work mode
- On-site
- Job type
- Full-time
- Seniority
- Lead
- Technologies
- Python, Google Cloud, AI / Machine Learning
- Language
- English-speaking role
Key requirements
- Execute quality iterations on reference agents identifying potential model or agent framework improvements.
- Source or facilitate creation of datasets for evaluation and training to improve model performance for Cloud customers.
- Design new agentic systems and context engineering algorithms, utilizing existing models and identifying the need for new training/evaluation objectives wher…
- Define and implement metrics that correspond to business problems.
- Prototype and iterate on the solution working closely with customers, product management and business development.
Hirepins insights
- Python is asked for in 21% of the 14 live IT jobs in Switzerland on Hirepins.
- Google Cloud is asked for in 21% of the 14 live IT jobs in Switzerland on Hirepins.
- 2 other Data Scientist roles are open in Switzerland on Hirepins right now.
About this role
The Staff Software Engineer, AAI Research role at Google Cloud focuses on building and improving agentic systems powered by Large Language Models. It suits experienced engineers with deep LLM expertise who enjoy research, data-driven quality loops, and customer‑focused prototyping.
Key details
- Location: Schweiz
- Level: Senior
What you'll do
- Execute quality iterations on reference agents identifying potential model or agent framework improvements.
- Source or facilitate creation of datasets for evaluation and training to improve model performance for Cloud customers.
- Design new agentic systems and context engineering algorithms, utilizing existing models and identifying the need for new training/evaluation objectives where necessary.
- Define and implement metrics that correspond to business problems.
- Prototype and iterate on the solution working closely with customers, product management and business development.
What you'll need
Must have
- Bachelor's degree or equivalent practical experience.
- 8 years of experience working with Large Language Models (LLMs) and building agents.
Nice to have
- Solid understanding of essential concepts such as tokens, context, Retrieval-Augmented Generation (RAG), and function calling.
- Solid understanding of core ML concepts, training algorithms, and best practices for evaluation.
- Strong understanding of data and familiarity with basic statistical analysis concepts (e.g., variance, p-value, bias) and general data science principles.
- Familiarity with running quality interactions, involving understanding business goals, defining technical metrics, implementing evaluation frameworks, designing experiments, analyzing results, performing RCAs, formulating hypotheses, and conducting ablation or live experiments.
- Proficiency in Python.
Tech stack
Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), function calling, Python
How to stand out for this role
Likely interview topics
- Design and optimization of LLM‑driven agent architectures.
- Defining and measuring business‑aligned evaluation metrics for AI systems.
- Data engineering for creating and curating evaluation/training datasets.
- Understanding and applying Retrieval‑Augmented Generation and function calling concepts.
- Python code quality and scalability for production‑ready AI pipelines.
Keywords to mirror in your CV
Large Language Models (LLMs), agentic systems, function calling, Python, statistical analysis, quality iteration, evaluation framework
What to show
- A prototype LLM agent that uses Retrieval‑Augmented Generation and custom function calling, with documented design decisions.
- An end‑to‑end evaluation pipeline that defines business‑driven metrics, runs experiments, and presents analysis (including variance, p‑values, RCAs).
- A curated dataset and data‑engineering workflow used to improve model performance for a specific Cloud use case.
How to apply
Use the "Apply on company website" button to continue to Google's careers page and submit your application there.
Source: Adzuna