Software Engineer, Automatic Prompt Optimization, AI Answers Quality
Company: Google
Locations: Mountain View, California, United States; New York, New York, United States
Salary: $147K – $210K a year
Work arrangement: On-site
Employment type: Full-time
Experience: 2-5 years
Education: bachelor degree
Posted: 2026-11-19
Responsibilities
Design and build automated workflows to optimize search prompts and improve the factuality of AI-generated responses. Facilitate model upgrades and fine-tuning while addressing complex loss patterns to ensure high-quality output.
Requirements
Requires a bachelor's degree and at least two years of software development experience. Candidates must have specific experience with Large Language Models, recommendation systems, and statistical evaluation methods.
Skills
- Software development
- Large Language Models
- Recommendation systems
- Generative AI
- Data structures
- Algorithms
- Statistical inference
- Hypothesis testing
- Prompt engineering
- Win-loss pattern analysis
- Ranking losses
- Evaluation metrics
- Information retrieval
- Distributed computing
- System design
- Natural language processing
Benefits
- Bonus
- Equity
- Health Insurance
About this role
MINIMUM QUALIFICATIONS:
* Bachelor’s degree or equivalent practical experience.
* 2 years of experience with software development in one or more programming
languages.
* 1 year of experience with Large Language Models (LLMs) and building quality.
* 1 year of experience building and deploying recommendation systems models
(retrieval, prediction, ranking, personalization, search quality, embedding)
in production.
* Experience integrating generative AI tools or LLM interfaces into workflows.
PREFERRED QUALIFICATIONS:
* 2 years of experience with data structures and algorithms.
* Experience applying statistical inference, confidence intervals, and
hypothesis testing to evaluate model changes and prevent overfitting.
* Experience balancing precision, recall, latency, and accuracy when
configuring prompt architectures.
* Experience with prompt engineering, LLMs, and win-loss pattern analysis.
* Experience utilizing statistical metrics, ranking losses, and evaluation
metrics to score LLM outputs.
* Experience developing accessible technologies.
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.
AI Overviews (AIO) and AI Mode (AIM), collectively AIX, are among Search’s
fastest-growing product areas, bringing generative AI-powered experiences
directly to Google Search. As we continue to scale, our mission remains vital:
ensuring factuality and quality across all AIX experiences.
To support this rapid expansion, the Factuality APO (Automatic Prompt
Optimization) workstream is pioneering an agent-based self-improvement pipeline.
Join Google Search AI and work at the intersection of industry leading
global scale. We apply breakthrough research, leveraging models like Gemini, to
launch high-impact products that help billions ask any question and get things
done. If you want to drive the future of AI in Search and work with world-class
experts to deliver tangible, global impact and continuous innovation, this is
the place.Individual pay is determined by factors including job-related skills,
experience, and relevant education or training.
US: $147000 - $210000 (USD) + 15% bonus target + equity + benefits
Learn more about benefits at Google
[https://www.google.com/about/careers/applications/benefits/].
RESPONSIBILITIES:
* Design comprehensive reward objectives to balance factuality with overall
response helpfulness and quality in alignment with performance goals.
* Build automated workflows to audit search prompts and identify opportunities
for continuous factuality self-improvement.
* Facilitate smooth large-model upgrades and orchestrate model fine-tuning
focused on factuality.
* Address complex loss patterns systematically using established factuality
taxonomies to achieve targeted quality improvements.
* Write product or system development code.
About Google
Software Development · 10,001+ employees · headquartered in Mountain View, CA