AI Agent Evaluation Engineer

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 the team uses to talk about failures precisely; run calibration sessions and measure inter-rater agreement.

• 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 (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 (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 against human labels before trusting it; treat judge error as the primary measurement risk.

• 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 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: 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 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, backend engineers, product managers, and the voice/language engineering team to turn findings into prioritized recommendations.

• 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.

…