Staff AI Systems Engineer - LLM, Evaluation, Equity

Maven

San Jose (CA)

On-site

USD 180,000 - 240,000

Full time

5 days ago
Be an early applicant

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Physical Health Benefits
Mental Health Benefits
Emotional Health Benefits
Financial Health Benefits
Work-life Balance Support
Community Contribution Opportunities
Bonus
Equity

Job summary

Zoom is seeking an experienced software engineer to improve the quality, reliability, and performance of its AI-powered virtual agent. You will diagnose AI agent failures, optimize prompt architectures, and build evaluation pipelines to measure agent quality.

This role requires deep expertise in large language models, system design, and end-to-end evaluation. You will collaborate with research and platform teams to deliver production-grade solutions that scale.

Qualifications

  • Candidates need 10+ years of software engineering experience, including 3-5 years specifically with production-grade LLM or conversational AI systems.
  • An advanced degree in Computer Science or Engineering is required or equivalent practical experience.

Responsibilities

  • Diagnose AI agent failures and issues in production systems.
  • Improve the quality, reliability, and performance of Zoom's AI-powered virtual agent.
  • Build evaluation pipelines to measure agent quality and track improvements.

Skills

System Architecture
LLM-based Systems
Conversational AI
Prompt Engineering
Evaluation Pipelines
Machine Learning
Context Management
Prompt Chain Optimization

Education

Advanced degree in Computer Science or Engineering

Tools

DSPy
APO
GEPA

Job description

Zoom is seeking an experienced software engineer to improve the quality, reliability, and performance of its AI-powered virtual agent. You will diagnose AI agent failures, optimize prompt architectures, and build evaluation pipelines to measure agent quality.

This role requires deep expertise in large language models, system design, and end-to-end evaluation. You will collaborate with research and platform teams to deliver production-grade solutions that scale.

Get your free, confidential resume review.
or drag and drop your file here.
Similar jobs

Similar jobs worth comparing

Staff Software Engineer — AI Agent Reliability & Scale
Staff Software Engineer — AI Agent Reliability & Scale

Zoom • United States

Hybrid
USD 147,000 - 339,000
Hybrid work environment
Career growth
Staff Software Engineer
Staff Software Engineer

Maven • San Jose (CA)

On-site
USD 180,000 - 240,000
Physical Health Benefits
Mental Health Benefits
Emotional Health Benefits
+5
Senior AI Engineer — LLM Evaluation & Production Systems
Senior AI Engineer — LLM Evaluation & Production Systems

LawPro.ai • Virginia (MN)

On-site
USD 140,000 - 200,000
Senior AI Engineer: LLM Evaluation & Production
Senior AI Engineer: LLM Evaluation & Production

LawPro.ai • Georgia

On-site
USD 140,000 - 210,000
Senior AI Engineer: LLM Evaluation & Production
Senior AI Engineer: LLM Evaluation & Production

LawPro.ai • Town of Florida (NY)

On-site
USD 140,000 - 210,000
Staff AI Agent Quality Engineer
Staff AI Agent Quality Engineer

Zoom • San Jose (CA), Northern (KY)

Hybrid
USD 147,000 - 339,000
Senior AI Services Platform Engineer (Remote)
Senior AI Services Platform Engineer (Remote)

Pantera Capital • San Jose (CA)

Hybrid
USD 151,000 - 333,000
Senior AI Engineer - Production LLM EvalOps
Senior AI Engineer - Production LLM EvalOps

LawPro.ai • Town of Texas (WI)

On-site
USD 140,000 - 210,000
Senior AI Systems Engineer - Remote Virtual Agent Quality
Senior AI Systems Engineer - Remote Virtual Agent Quality

Pantera Capital • San Jose (CA)

Hybrid
USD 147,000 - 339,000
Senior AI Quality Engineer — LLMs & Evaluation Systems
Senior AI Quality Engineer — LLMs & Evaluation Systems

Block • San Francisco (CA)

On-site
USD 190,000 - 230,000