We are looking for a Data Engineer to join our Data practice and build and maintain the data pipelines and models that power client analytics, personalization, and AI products. You will work within the architecture and standards established by the Lead Data Engineer and collaborate with Data Scientists, Product, and Strategy teams. Your responsibilities will also include preparing data for agentic AI applications and incorporating AI agents into your engineering workflows.

Key Responsibilities

• Build, test, and maintain batch and streaming data pipelines using Snowflake, AWS Redshift, and Google Cloud Platform services, including BigQuery, Dataflow, Pub/Sub, and Cloud Composer.

• Ingest data from client APIs, SaaS platforms, event streams, and databases into governed cloud storage and data warehouse layers.

• Develop data transformation logic using SQL and Python, and implement well-tested, documented data models with dbt.

• Build datasets and dashboards in Sigma to enable business users and AI agents to query data.

• Prepare and serve data for agentic AI use cases, including feature tables, embeddings, and retrieval datasets, and make data accessible to agents through governed APIs and MCP servers.

• Leverage AI coding agents and automated workflows to accelerate development, testing, and documentation, while reviewing outputs for accuracy and correctness.

• Implement data quality checks, monitoring, and alerting, and develop automated, agent-assisted processes for triaging pipeline failures.

• Document data pipelines, schemas, and definitions to ensure they are accessible and understandable to other teams and AI agents.

• Participate in code reviews and sprint planning as part of an agile, globally distributed team.

Requirements

• At least 1 year of professional Data Engineering experience building and operating production data pipelines.

• Strong SQL skills and working proficiency in Python.

• Hands-on experience with a cloud data warehouse such as Snowflake, AWS Redshift, or BigQuery. Exposure to a second platform is an advantage.

• Experience using dbt for data modeling and transformation.

• Experience with a BI or semantic layer tool; familiarity with Sigma is a plus.

• Experience with data orchestration tools such as Airflow, Cloud Composer, or Dagster.

• Experience with Git and CI/CD workflows.

• Familiarity with how LLMs, embeddings, vector search, and AI agents consume and utilize data, along with an interest in building data solutions for agentic applications.

• Experience using AI coding assistants or agents as part of daily engineering workflows.

• Ability to work with APIs and semi-structured data formats such as JSON, Parquet, and Avro.

• A Bachelor's degree in Computer Science, Engineering, or equivalent professional experience.

• Advanced English proficiency for collaboration with global teams.