We are looking for a Software Engineer with strong Python development skills and hands-on experience building and operating Retrieval-Augmented Generation (RAG) systems.
The ideal candidate will have practical experience across the RAG lifecycle, including retrieval, embeddings, and LLM-backed generation. Familiarity with Azure services, Databricks, and connector ecosystems used to integrate enterprise data sources will be highly valuable.
Key Responsibilities
Design, develop, and maintain software solutions using Python.
Build and operate RAG-based applications and systems.
Develop and manage retrieval pipelines, embedding workflows, and LLM-backed generation.
Integrate RAG solutions with enterprise data sources and applications.
Work with Azure services, including Blob Storage and Azure Core Tools.
Work with Databricks for data processing and engineering requirements.
Integrate and work with connector ecosystems across platforms such as:
Confluence
SharePoint
ServiceNow
ServiceCloud
Zendesk
Troubleshoot and optimize RAG systems for reliability, scalability, and performance.
Collaborate with engineering and cross-functional teams to understand requirements and deliver effective solutions.
Follow software engineering best practices for development, testing, deployment, and maintenance.
Must-Have Skills
Solid hands-on experience with Python.
Hands-on experience building and operating RAG systems.
Robust understanding of RAG components, including:
Retrieval
Embeddings
LLM-backed generation
Experience developing and integrating AI/LLM-based applications.
Familiarity with Azure services, particularly Blob Storage and Azure Core Tools.
Working knowledge of Databricks.
Experience working with enterprise data connectors or integration ecosystems.
Robust problem-solving and analytical skills.