Chipton-Ross is looking for an AI Data Engineer for a permanent remote position.
POSITION OVERVIEW :
As an AI Data Engineer, you will work directly with our Enterprise Architect to implement the data infrastructure essential for agentic AI applications, including data pipelines that support AI agent memory and learning capabilities. You'll collaborate with cross-functional teams to ensure data systems meet the needs of our AI initiatives and work towards automating tasks to improve recruiter productivity. This role is ideal for someone eager to grow in the emerging field of agentic AI while developing robust data engineering skills.
KEY RESPONSIBILITIES :
- Implement and maintain data pipelines that support AI agent memory and context persistence
- Assist in developing data models for candidate profiles and interaction histories
- Set up and configure vector databases for semantic search capabilities
- Build data transformation processes for embedding generation and storage
- Support the implementation of retrieval-augmented generation (RAG) architectures
- Assist with the deployment of AI agent frameworks (LangGraph, Crew AI, AutoGen, LangChain)
- Maintain on-premise MSSQL databases and implement efficient data processing workflows
- Create and optimize data retrieval systems for conversation state management
- Support the development of knowledge graph implementations
- Implement and maintain semantic caching systems
- Document data flows and architectures according to enterprise standards
- Collaborate with the Enterprise Architect to ensure implementations align with architectural vision
REQUIRED SKILLS & QUALIFICATIONS :
Bachelor's degree in Computer Science, Data Science, or related fieldExperience in data engineering or related roleProficiency in Python and SQLExperience with ETL / ELT processes and data pipeline developmentFamiliarity with database systems, particularly MSSQLUnderstanding of data modeling principlesBasic knowledge of AI / ML conceptsStrong problem-solving skills and attention to detailExcellent communication skills and ability to work in a team environmentDESIRED SKILLS :
Vector databases (Chroma, Weaviate, Pinecone)Embedding models and techniquesEnterprise AI platforms (Azure OpenAI, AWS Bedrock)Graph databases (Neo4j, Amazon Neptune)LLM frameworks and architecturesData versioning and lineage trackingExperience with :Containerization (Docker)CI / CD pipelines for data workflowsCloud data services (Azure Data Factory, AWS Glue)Version control systems (Git)Data documentation toolsEDUCATION :
Bachelor's (Required)