Principal Applied AI Engineer - Entity Agents
Company: ZoomInfo Technologies LLC
Location: Remote
Source: We Work Remotely
About ZoomInfo
ZoomInfo is where careers accelerate. We move fast, think boldly, and empower you to do the best work of your life. You’ll be surrounded by teammates who care deeply, challenge each other, and celebrate wins. With tools that amplify your impact and a culture that backs your ambition, you won’t just contribute, you’ll make things happen, fast.
The Opportunity
ZoomInfo’s Core Data team builds the company and contact data behind the Go-To-Market Intelligence Platform: hundreds of millions of records, resolved to the right entity, kept accurate, and delivered to more than 35,000 customers.
Core Data is moving to AI-native data management, where an agent pursues the evidence for an entity, decides every attribute, and records the reasoning. We are hiring a Principal Applied AI Engineer to build the machinery that runs these agents at production volume, validates every version before it ships, and enables researchers and product managers to operate them independently.
What You’ll Do
- Run the benchmark and golden-gate system: Move judge runs, golden-gate results, arms scorecards, and cost-per-record metrics from a laptop to a scheduled system against staging. Ensure every agent version is gated automatically with variance and drift tracked per release.
- Complete the entity-agent pipeline: Build missing stages such as enricher fan-out, location sets, and hierarchy batch files. Migrate classifiers to a shared runner to ensure production-scale performance.
- Build the evidence adapters: Create a unified envelope for registries, live web, mail-tenant signals, and external research vendors. Ensure these are replayable, swappable, and measured for lift.
- Deploy onto the ZoomInfo Agentic Platform (ZAP): Carry agents through the production plan, build ingest adapters, and maintain rollback paths per version.
- Make the loop self-service: Build review queues, tagging tools, blast-radius viewers, and batch runners for non-engineers.
- Keep agent surfaces alive: Own the health and deployment of classifiers, agent hubs, and judge platforms to ensure the team’s iteration cycle is never blocked.
- Instrument everything: Track cost per call/row/stage, quality per version, and implement proactive alerting.
What You’ll Bring
- 5+ years of software engineering experience, including at least 2 years shipping LLM-based systems to production (agent loops, tool use, retrieval, structured output, and evaluation harnesses).
- Strong proficiency in Python and TypeScript, with comfort across API layers, batch runners, and internal web UIs.
- Experience building platforms for others to operate, focusing on replayability, idempotency, and observability.
- Working knowledge of data pipelines and entity resolution (ingestion, matching, and serving).
- A track record of taking prototypes to production while maintaining strict adherence to benchmarks and test sets.
- A "bias for action" and the tenacity to navigate a fast-moving, distributed organization.
Preferred Qualifications
- Experience with B2B company/contact data, identity data, or entity resolution at scale.
- Experience with Claude or comparable frontier models, agent frameworks, and eval harnesses.
- Experience deploying agents onto an internal orchestration layer.
- Background at an AI-native startup or a data infrastructure company.
Who You Are
- A builder who ships: You prioritize functional, running adapters over design documentation.
- An evaluator by instinct: You do not release code without a test set, a threshold, and a cost analysis.
- A platform thinker: You design systems for scalability and vendor independence.
- Comfortable in the data: You understand the nuances of matching logic and the impact of false merges versus missed matches.
- Tenacious: You are capable of driving work to completion in a complex, distributed environment.
- One team: You are honest, supportive, and celebrate collective wins and losses.
Compensation
US Base Salary Range: $171,500 – $269,500 USD. Actual compensation is based on factors such as work location, qualifications, skills, and experience. Additional compensation such as bonus, commission, and equity may apply.
The Environment
You will report to the Senior Manager of Product for Core Data, with the Principal AI Engineer as your technical lead. You will partner closely with product managers, the research team, and the agentic platform team.
About ZoomInfo
ZoomInfo (NASDAQ: GTM) is the Go-To-Market Intelligence Platform that empowers businesses to grow faster with AI-ready insights, trusted data, and advanced automation.
ZoomInfo is an equal opportunity employer. We are committed to providing equal employment opportunities regardless of sex, race, age, color, national origin, sexual orientation, gender identity, marital status, disability status, religion, protected military or veteran status, or any other characteristic protected by applicable law.
To apply: Click here to submit your application