AI Agent Evaluation Engineer

Cresta

Oregon

Hybrid

USD 120,000 - 180,000

Full time

7 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Medical, dental & vision
Flexible PTO
Parental leave
Retirement plan
Remote work setup budget
Wellness stipend
In-office meal program

Job summary

Cresta in Oregon is seeking an AI Agent Evaluation Engineer to define quality, build scalable evaluation systems, and measure performance of our AI receptionist across conversations. You will annotate data, design metrics, calibrate judges, and collaborate with engineers, product, and language teams to improve reliability and user experience.

This role blends hands-on analysis with engineering execution in a fast-moving AI company, with opportunities to influence product direction and customer

Qualifications

  • 3+ years in software engineering, applied ML, or data-intensive research with 1–2 years hands-on with LLMs in production.
  • Bachelor’s or Master’s in CS, Computational Linguistics, Cognitive Science, Statistics, or equivalent practical experience.
  • Built and operated an end-to-end evaluation system for a production LLM product: rubric, labels, automated judges, regression suite.
  • Deep understanding of evaluation methodology: golden sets, judges, regression suites, and calibration.
  • Fluent in at least one language other than English; reading a trace to understand agent actions.
  • Strong Python programming skills; able to build evaluation tooling independently; fine-tuning not required.
  • Willing to do non-scalable work weekly: label conversations, build a failure taxonomy from scratch.
  • Strong written communication; author the guidelines others follow.

Responsibilities

  • Define and maintain the evaluation rubric across adherence, outcome, and conversation experience.
  • Write the annotation guidelines and failure taxonomy; run calibration sessions and measure inter-rater agreement.
  • Classify and prioritize failure modes by severity and frequency.
  • Review production conversations weekly; cluster failures for automated evaluations.
  • Trace each failure to its likely cause and route to the right owner with evidence.
  • Evaluate across languages and report quality by segment (language, accent, audio quality, intent).
  • Build and operate the evaluation pipeline that scores every production conversation.
  • Calibrate automated judges against human labels; treat judge error as a risk.
  • Design sampling strategies to ensure reported quality changes are real.
  • Build and maintain the golden set and regression suite for validation.

Skills

Python
LLM experience
Data analysis
Communication
Prompting

Education

BSc/MSc in CS/Computational Linguistics/Statistics

Tools

Python
LLM APIs

Job description

Cresta unlocks the true potential of the customer experience, turning every conversation into a competitive advantage. Cresta’s unified AI platform combines conversational AI agents, real-time human agent augmentation, and comprehensive conversation intelligence to drive revenue and efficiency gains across every channel. The world’s leading companies, including United Airlines, Cox Communications, and Marriott, use Cresta to power world-class customer experiences every day.

Born from the Stanford AI Lab, Cresta has raised more than $270 million from the world’s leading investors, including a16z, Greylock, and Sequoia. Cresta’s leadership includes some of the leading minds in AI today. Our CEO, Ping Wu, founded and led Google's Contact Center AI and Vertex AI platforms before joining Cresta to build the future of AI-driven customer experiences.

Over the next few years, AI is going to redefine how people all over the world interact with businesses every day. Come build that future at Cresta.

About the role

Cresta’s AI Receptionist answers the phone for small businesses that would otherwise miss the call. It handles millions of conversations a month today, making sure no call goes unanswered and helping owners complete the front-office tasks that keep their business running, and it does so across hundreds of customers. Whether those conversations are actually good is the single most important question in the business, and it deserves a full-time owner. That’s you.

As our first AI Agent Evaluation Engineer, you define what quality means for every agent we run, you build the systems that measure it across every conversation, and you are the person the company trusts when the question is “how good is it, really?”

The work combines hands-on conversation analysis, rigorous evaluation design, and engineering execution: reading and annotating real conversations to learn how the agent actually fails, building the automated evaluation systems (LLM-based judges, golden sets, regression suites) that measure those failures at scale, and keeping those systems honest by calibrating them against human judgment. Fixing what you find is welcome but not the core of the job; an accurate, prioritized picture of agent quality is.

What You'll Do
Evaluation Design & Quality Definition

Define and maintain the evaluation rubric for the agent across three axes: adherence (did it follow its design, call the right tools, respect guardrails), outcome (did the conversation achieve its goal), and conversation experience (latency, turn-taking, tone, repetition).

Write the annotation guidelines and failure taxonomy

Write the annotation guidelines and failure taxonomy the team uses to talk about failures precisely; run calibration sessions and measure inter-rater agreement.

Classify and prioritize failure modes

Classify and prioritize failure modes by severity and frequency so engineering and product work on what matters most.

Conversation Analysis & Annotation

Review production conversations by hand every week, leverage QA partners; open-code failures, cluster them, and turn the clusters into the evaluations worth automating.

Trace each failure to its likely cause

Trace each failure to its likely cause (prompt, knowledge gap, tool or flow bug, speech recognition) and route it to the right owner with enough evidence to act on.

Evaluate across languages and report quality by segment

Evaluate across languages and report quality by segment (language, accent, audio quality, intent), not just in aggregate.

Scalable Evaluation Systems

Build and operate the evaluation pipeline that scores every production conversation, combining automated checks, LLM-based judges, and human review.

Calibrate every automated judge

Calibrate every automated judge against human labels before trusting it; treat judge error as the primary measurement risk.

Design sampling strategies

Design sampling strategies (stratified by intent, language, caller type, audio conditions) so that reported changes in quality are real.

Build and maintain the golden set and regression suite

Build and maintain the golden set and regression suite that every prompt, model, knowledge, and flow change is validated against before release.

Coverage & Edge Cases

Maintain the failure-mode coverage map: which behaviors are tested, partially tested, or unmeasured; close the gaps.

Design evaluations for behaviors no standard harness covers

Design evaluations for behaviors no standard harness covers: high-stakes conversation types such as handoffs to a human, misuse and unwanted-caller handling, and resilience under upstream failures.

Define the quality and latency thresholds

Define the quality and latency thresholds the agent is held to.

Reporting & Cross-Functional Collaboration

Report quality trends to internal stakeholders and customers clearly, with uncertainty stated and without burying bad news.

Partner with forward-deployed engineers

Partner with forward-deployed engineers, backend engineers, product managers, and the voice/language engineering team to turn findings into prioritized recommendations.

Document methodology so results are reproducible

Document methodology so results are reproducible and the evaluation practice outlives any one person.

What We're Looking For

3+ years of professional experience in software engineering, applied ML, or data-intensive research roles, including at least 1–2 years working hands-on with LLM-based systems in production.

Bachelor’s or Master’s degree in Computer Science, Computational Linguistics, Cognitive Science, Statistics, or a related field, or equivalent practical experience.

Built and operated an end-to-end evaluation system for a production LLM product (agent or otherwise): rubric, human labels, automated judge, regression suite.

Deep understanding of evaluation methodology: what golden sets, judges, regression suites, and calibration are for, and when each fails. Tool-agnostic; you will work in our in-house tooling.

Fluent in how LLM agents work: prompts, tool calls, context handling, multi-turn state. You can read a trace and tell what the agent was doing and why.

Strong programming skills in Python and experience with LLM APIs; able to build and ship evaluation tooling independently. Fine-tuning and ML frameworks are not required.

Able to write a rubric that independent reviewers would score the same way, and to measure whether they do.

Able to design a test from an open-ended quality question: you decide what to measure and how, rather than executing a predefined plan.

Willing to do non-scalable work weekly, both yourself and by directing our QA partners: listening to calls, labeling conversations, building a failure taxonomy from scratch.

Professional fluency in at least one language other than English, sufficient to evaluate multilingual agent behavior directly.

Strong written communication; you author the guidelines others follow.

Note on Our Hiring Process

We highly value your time and engineering craftsmanship. To ensure a streamlined and objective process, the first step for qualified applicants following an initial resume review is a self-paced CoderPad technical assessment. This allows you to showcase your practical coding and problem-solving skills in a real-world environment before moving into conversational interview rounds.

Perks & Benefits

We offer a comprehensive and people-first benefits package to support you at work and in life:

  • Comprehensive medical, dental, and vision coverage with plans to fit you and your family
  • Flexible PTO to take the time you need, when you need it
  • Paid parental leave for all new parents welcoming a new child
  • Retirement savings plan to help you plan for the future
  • Remote work setup budget to help you create a productive home office
  • Monthly wellness and communication stipend to keep you connected and balanced
  • In-office meal program and commuter benefits provided for onsite employees
Compensation at Cresta

Cresta’s approach to compensation is simple: recognize impact, reward excellence, and invest in our people. We offer competitive, location-based pay that reflects the market and what each individual brings to the table.

The posted base salary range represents what we expect to pay for this role in a given location. Final offers are shaped by factors like experience, skills, education, and geography. In addition to base pay, total compensation includes equity and a comprehensive benefits package for you and your family.

Our use of AI in recruiting

We may use AI tools in our recruiting process, which require human review and oversight. If you have questions about our use of AI or wish to opt out, please contact

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

AI Agent Evaluation Engineer
AI Agent Evaluation Engineer

Cresta • Marion (KS)

Remote
USD 120,000 - 180,000
AI Agent Evaluation Engineer
AI Agent Evaluation Engineer

Cresta • San Francisco (CA)

Remote
CAD 90,000 - 140,000
Medical, dental, vision
Flexible PTO
Parental leave
+4
Senior Machine Learning Engineer
Senior Machine Learning Engineer

FDE Times • United States

Remote
USD 205,000 - 270,000
Medical coverage
Dental coverage
Vision coverage
+6
Principal Solutions Engineer, West
Principal Solutions Engineer, West

Big Internet Seller Services Inc • United States

Remote
USD 220,000 - 275,000
Comprehensive medical, dental, and vis
Flexible PTO
Parental leave
+4
Principal Solutions Engineer, West
Principal Solutions Engineer, West

FDE Times • United States

Remote
USD 220,000 - 275,000
Health insurance
Flexible PTO
Parental leave
+4
Principal Solutions Engineer (Remote)
Principal Solutions Engineer (Remote)

Cresta • United States

Remote
USD 220,000 - 275,000
Comprehensive health benefits
Flexible PTO
Paid parental leave
+4
Lead Engineer - AI Agent Voice Experience
Lead Engineer - AI Agent Voice Experience

FDE Times • United States

Remote
USD 205,000 - 270,000
Comprehensive medical, dental, and vis
Flexible PTO
Parental leave
+3
Solutions Engineer, AI Agent (Strategic)
Solutions Engineer, AI Agent (Strategic)

FDE Times • United States

Remote
USD 220,000 - 275,000
Comprehensive medical, dental, and R&I
Flexible PTO
Paid parental leave
+4
AI Strategist
AI Strategist

FDE Times • United States

Remote
USD 150,000 - 200,000
Comprehensive medical, dental, and vis
Flexible PTO
Parental leave
+4
Senior Forward Deployed Engineer (AI Agent)
Senior Forward Deployed Engineer (AI Agent)

FDE Times • United States

Hybrid
USD 185,000 - 235,000
Comprehensive medical, dental, and/or视
Remote work setup budget
Flexible PTO
+4