Principal Applied AI Engineer – Entity Agents

This is a fully remote position, open to applicants in United States.

📋 Description

• Execute the benchmark and golden-gate system on a scheduled basis against staging, automatically managing agent versions and tracking variance and drift.

• Finalize the entity-agent pipeline, which involves enricher fan-out, location sets, hierarchy batch files, and migration of production-scale classifiers.

• Assess throughput and unit costs for each pipeline stage within designated cohorts.

• Develop evidence adapters for registries, live web, mail-tenant signals, and external research vendors, ensuring a replayable and swappable envelope.

• Implement company and contact agents on ZoomInfo’s Agentic Platform, which includes ingest adapters, bulk intake processes, rollback pathways, and synchronized implementation upgrades.

• Create review queues, tagging tools, blast-radius viewers, and batch runners for self-service utilization by researchers and product managers.

• Oversee the health and deployment of classifiers, agents hub, and judge platform within internal tools.

• Measure cost, latency, quality, and alerts across various systems.

• Collaborate with the Principal AI Engineer, product managers, research team, agentic platform team, and the company and person engineering teams.

• Report directly to the Senior Manager of Product for Core Data, with the Principal AI Engineer serving as the technical lead.

⛳️ Requirements

• A minimum of 5 years of software engineering experience, including at least 2 years of deploying LLM-based systems into production.

• Proficient in agent loops, tool utilization, retrieval processes, structured output, and evaluation harnesses.

• Strong skills in Python and TypeScript.

• Comfortable working with an API layer, batch runners, and a small web UI for internal users.

• Experience in building platforms that others can operate, including adapters, runners, queues, or internal tools designed for replay, idempotency, and observability.

• Familiarity with data pipelines and entity resolution.

• Proven ability to transition prototypes to production while maintaining validated behaviors.

• Expertise in instrumentation, specifically in cost and latency budgeting.

• Experience with B2B company or contact data, identity or registry data, or large-scale entity resolution.

• Background with Claude or similar frontier models, agent frameworks, and evaluation harnesses (preferred).

• Experience deploying agents onto an internal agent platform or orchestration layer (preferred).

• Previous work experience at an AI-native startup, a forward-deployed or applied AI team, or a data infrastructure company (preferred).

🏝️ Benefits

• Comprehensive benefits package.

• Holistic programs for mind, body, and lifestyle designed to promote overall well-being.

• Additional compensation may include bonuses, commissions, and equity.