Analytics Engineer

Zof AI; San Francisco, Northern (CA, KY); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Zof AI is looking for an Analytics Engineer to build and operate production data pipelines that turn raw agent runs, test results, and remediation outcomes into trustworthy datasets. You will own the data layer beneath our control plane, including streaming and batch ingestion and warehouse models used for evals and analytics.

You will ensure data quality with lineage, tests, and cost-aware design while collaborating with AI and product teams to turn signals into reusable datasets for model

Qualifications

• Experience building and operating production data pipelines.
• Strong SQL and comfort modeling data in a warehouse.
• Proficiency in Python or a similar language for data work.
• Working knowledge of an orchestration tool such as Airflow, Dagster, or Prefect.
• Understanding of data quality, testing, and schema evolution.
• Judgment about freshness, cost, and correctness trade-offs.
• Clear written and verbal communication.
• High ownership of the systems you build.

Responsibilities

• Design and build ingestion pipelines for agent runs, defect reproductions, and remediation outcomes.
• Model and maintain the warehouse tables that evals, analytics, and product reporting depend on.
• Build streaming and batch paths that keep data fresh without sacrificing correctness.
• Own pipeline orchestration end to end, including scheduling, dependencies, retries, and backfills.
• Wire data quality checks, tests, and alerting into every pipeline you ship.
• Track lineage so every number we report traces back to its source evidence.
• Partner with AI and product engineers to turn raw signals into datasets they can build on.
• Own the cost, performance, and reliability of the data platform in production.

Skills

Data pipelines

SQL

Python

Orchestration tools

Data quality

Communication

Ownership

Tools

Airflow

Dagster

Prefect

dbt

Snowflake

BigQuery

Databricks

Job description

Zof AI is seeking an Analytics Engineer to build the pipelines that turn raw agent runs, test results, and remediation outcomes into data the company can trust. This role owns the data layer beneath our control plane: streaming and batch ingestion, the warehouse models that serve evals and analytics, and the quality checks and lineage that make every dataset defensible. If you have worked as an Analytics Engineer, ETL Developer, Big Data Engineer, or Data Platform Engineer, this is that discipline at Zof AI. The ideal candidate has built pipelines that other teams depend on daily and treats data quality as an engineering problem, not a cleanup task.

Engineering · Mid to Senior · Full-time · On-site · San Francisco, CA

Responsibilities

• Design and build ingestion pipelines for agent runs, defect reproductions, and remediation outcomes.
• Model and maintain the warehouse tables that evals, analytics, and product reporting depend on.
• Build streaming and batch paths that keep data fresh without sacrificing correctness.
• Own pipeline orchestration end to end, including scheduling, dependencies, retries, and backfills.
• Wire data quality checks, tests, and alerting into every pipeline you ship.
• Track lineage so every number we report traces back to its source evidence.
• Partner with AI and product engineers to turn raw signals into datasets they can build on.
• Own the cost, performance, and reliability of the data platform in production.

Requirements

• Experience building and operating production data pipelines.
• Strong SQL and comfort modeling data in a warehouse.
• Proficiency in Python or a similar language for data work.
• Working knowledge of an orchestration tool such as Airflow, Dagster, or Prefect.
• Understanding of data quality, testing, and schema evolution.
• Judgment about freshness, cost, and correctness trade-offs.
• Clear written and verbal communication.
• High ownership of the systems you build.

Nice to have

• Experience with streaming systems such as Kafka, Kinesis, or Pub/Sub.
• Experience with dbt, Snowflake, BigQuery, Databricks, or similar tooling.
• Experience preparing datasets for evals, fine-tuning, or model training.
• Experience standing up a data platform at an early-stage company.

Hands-on experience building data pipelines that feed AI, ML, or eval workloads is required