Senior GenAI Data Engineer (Databricks)

New

MexicoFull-TimeSenior

Salary not disclosed

Apply NowOpens the employer's application page

Job Details

Strong hands-on experience with Databricks Lakehouse architecture.
Advanced SQL skills and experience in data modeling at scale.
Experience integrating LLM APIs (e.g., OpenAI, Anthropic) into engineering workflows.
Practical experience building AI-driven features such as enrichment, anomaly detection, and classification.
Experience with frameworks like LangChain, LlamaIndex, or similar orchestration tools.
Knowledge of RAG systems and vector databases for semantic retrieval.
Understanding of tool/function calling for secure LLM-to-database/API interactions.
Exposure to prompt engineering and guardrailing techniques for reliable AI outputs.
Familiarity with CI/CD pipelines, GitHub workflows, and YAML-based configurations.
Strong problem-solving mindset with ability to operate autonomously in ambiguous environments.
Excellent communication skills and ability to collaborate across technical and non-technical teams.

Architect and deploy AI agents within the Databricks ecosystem for data enrichment, anomaly detection, and automated reasoning.
Build and maintain scalable data pipelines ensuring high data quality, reliability, and traceability.
Develop advanced SQL models and semantic layers to support analytics and business intelligence use cases.
Integrate LLM APIs such as OpenAI and Anthropic into production data workflows.
Develop “chat with your data” solutions enabling natural language querying over enterprise datasets.
Implement RAG pipelines using vector search and modern AI orchestration frameworks.
Collaborate with cross-functional teams (Product, Engineering, Analytics, Business) to deliver scalable data solutions.
Optimize performance, automation, and CI/CD processes for data and AI workflows.
Ensure strong governance, documentation, and maintainability across all data assets.

View Full Description & ApplyYou'll be redirected to the employer's site