Data Engineer | specialist
Core
Design and implement scalable, AI-driven data pipelines to modernize legacy systems and enable faster data transformation and migration.
Role type
Senior Data Engineer specializing in Generative AI and legacy modernization
Builds
Scalable data pipelines, AI automation tools, and metadata models for enterprise data strategy
Domain
Data Engineering, Artificial Intelligence, Generative AI, Legacy System Modernization
Deliverable
production ML models | infrastructure
Required skills
Generative AI, Large Language Models (LLMs), AI agents, RAG architectures, prompt engineering, function calling, tool use, automated AI workflows, orchestration frameworks (LangChain, LangGraph, Semantic Kernel, CrewAI), Python, PySpark, Spark SQL, SQL, Databricks, distributed data processing, data modeling, data warehouse architectures
Preferred skills
Experience with XML, JSON, YAML formats, declarative pipeline frameworks, Lakeflow Jobs
Technologies
Databricks, PySpark, Spark SQL, LangChain, LangGraph, Semantic Kernel, CrewAI, Lakeflow Jobs
Responsibilities
Define and implement AI-driven solutions for legacy system modernization; Build Generative AI solutions to automate documentation and migration workflows; Design intermediate metadata models representing business rules and data flows; Build and maintain scalable data pipelines using Databricks and declarative frameworks; Contribute to data governance, lineage, and quality improvements during migration; Collaborate with architects and engineers to design secure, high-performance solutions
Seniority
Senior, hands-on IC