Data Engineering Team Lead (Agentic Search)

Location: Israel

Department: Search

The Product:

In a rapidly evolving world, trust in AI depends on AI agents being grounded in fresh, verified real-world data. Search is the foundation that makes this possible.

We are building an agent-native search platform designed specifically for AI systems rather than human users. Our product provides programmatic, low-latency, and observable search APIs that AI agents use to retrieve, filter, and reason over real-world information at scale.

Behind every search request is a rich stream of signals - query patterns, retrieval decisions, crawling outcomes, ranking quality, usage and revenue events. Turning that stream into a trustworthy, queryable data platform is what makes the product improvable, the business measurable, and the models trainable.

The Role:

We are looking for a Data Engineering Team Lead to lead our data platform - both the data behind our search quality and ML pipelines, and the analytics that drive product and business decisions.

In this role, you will lead a team of data engineers and own the end-to-end data lifecycle: ingestion from production services, helping model and architect our data warehouse, and exposing clean, well-documented data to researchers, engineers, and analysts across the company.

The platform spans tens of terabytes and ingests from tens of proprietary and third-party sources - our own search engine and its components, CRM, billing, identity, and product analytics across multi-region production environments. Around 100 internal users rely on it daily.

You will lead our data platform, hire and grow the team, and stay hands-on enough to design and review the systems your team ships.

In this position, your responsibility will be to:

• Lead and architect Tavily's data platform - from real-time ingestion through data warehouse medallion layers to consumer-facing datasets and dashboards

• Lead, hire, mentor, and grow a team of data engineers; set engineering standards for code quality, testing, documentation, and on-call

• Work closely with engineers across the company to make sure batch and streaming pipelines are done correctly

• Define and implement observability for the data platform: data quality checks, freshness monitors, lineage, schema evolution, and cost controls

• Partner with researchers, engineers , analysts, finance, and product managers to deliver trustworthy datasets for product & gtm analytics.

• Define the objects, entities, and relationships that model Tavily's search domain - agent inputs, URLs, chunks, agent sessions, crawls, and the connections between them - and turn that mental model into a clean, queryable data model that the rest of the company can reason about.

• Data Governance: Can ensure the highest standards of data quality, integrity, and security across all environments.

You may be a good fit if you:

• 5+ years of Data Engineering experience, with a focus on designing and implementing scalable, analytics-ready data models and cloud data warehouses (e.g., BigQuery, Snowflake).

• Have hands-on experience with Snowflake (or a comparable cloud data warehouse) and a strong grasp of data warehouse architecture preferably medallion schema.

• Deep knowledge of databases (schema design, query optimization) and familiarity with NoSQL use cases.

• Expertise in modern data orchestration and transformation frameworks (e.g., Airflow, DBT).

• Solid understanding of cloud data services (e.g., AWS, GCP) and streaming platforms (e.g., Kafka, Pub/Sub).

• Have hands-on experience with the Spark / MapReduce paradigm and understand when distributed processing is the right tool

• Are fluent in Python and SQL for production data work

• Have operated data systems in production: debugged them under pressure, recovered from data incidents, and understand what it means to backfill a corrupted table.