Remote Gen AI Engineer (AWS)

Required Skills & Experience

• 8+ years of experience with 5+ years of Data Engineering experience
• 2+ years of hands-on experience developing and deploying Generative AI applications.
• Strong Snowflake expertise, including advanced SQL, Tasks/Streams, stored procedures, and performance tuning.
• Hands-on experience with Snowflake Cortex AI (or an equivalent production LLM platform).
• Experience developing Snowflake Native Apps using the Snowflake Native App Framework (e.g., Snowpark with Python/Scala, application packaging, versioning, upgrades, and secure distribution patterns).
• Strong AWS experience, including S3, Lambda, Glue, Step Functions, DynamoDB, EC2, CloudFormation, and Kinesis.
• Strong Python proficiency (production-grade code, testing, packaging).
• Experience with CI/CD tools such as GitHub Actions and/or Jenkins; and IaC with Terraform and/or CloudFormation.
• Experience building structured extraction pipelines from free-text inputs at scale (parsing, validation, deduplication, and quality controls).
• Experience implementing ML/LLM observability in a production environment as a Gen AI Engineer, implementing calling LLMs, and evaluating the LLM output

Nice to Have Skills & Experience

Relevant certifications are a plus (AWS, Snowflake) Cortex AI DataDog AI Observability tooling Experience in hospitality, customer profile, personalization, or preference management domains. Experience with human-in-the-loop workflows and taxonomy-driven classification systems. Familiarity with data privacy and compliance requirements for customer data. Experience with Snowflake governance and security patterns (e.g., RBAC, masking policies, row access policies, tagging). Experience with automated regression testing for prompts and LLM outputs (prompt evaluation frameworks). Experience with Snowpark Container Services or containerized ML/AI services operating close to data.

Job Description

The Senior AI Data Engineer will join this global hotel company's Data Engineering team to deliver data and AI capabilities for key initiatives. This role partners closely with Data Product Management, and Data Science to design, build, and operationalize scalable ingestion, transformation pipelines, GenAI-enabled pipelines in Snowflake and AWS.

POSITION RESPONSIBILITIES:

• Design and implement ingestion pipelines from multiple source systems into Snowflake using AWS services and Python.
• Build and optimize SQL-based transformation pipelines for free-form text cleansing, normalization, and deduplication.
• Implement Snowflake Cortex AI workflows for classification, extraction, and structured data generation.
• Develop robust prompt versioning, response parsing, validation, and fallback logic.
• Snowflake Native App Development : Build and deploy Snowflake Native Apps to package data/AI capabilities; manage application objects, permissions, versioning, upgrades, and release workflows; integrate Snowpark-based logic and CI/CD for repeatable delivery.
• Define, instrument, and track data and model quality KPIs, including precision, recall, coverage, drift, and error rates.
• Integrate Arize (or a comparable platform) for observability, monitoring, and root-cause analysis of model behavior.
• Support production rollout and operational readiness: deployment automation, runbooks, documentation, and handoff to internal teams.