Role Overview
We're seeking a highly skilled software engineer to contribute to the development of scalable, distributed systems.
Key Responsibilities
- Design and implement microservices for data ingestion, vector indexing, retrieval APIs, inference orchestration, and human validation workflows.
- Develop APIs using Python/Node.js and integrate parallel search workflow with new AI inference pipelines.
- Implement schemas and objects for the feedback loop database and ensure proper handling of PII, masking, and secure data retention policies.
- Contribute to infrastructure as code deployments, write unit/integration tests, participate in performance tuning and load testing, and support continuous integration/continuous deployment pipelines.
Technical Requirements
- Proficiency in Python (preferred), Node.js, Java, or .NET is essential.
- Azure Functions, Azure Data Factory, Azure Event Hub, Service Bus, and Azure SQL experience are mandatory.
- Familiarity with RAG architectures, SharePoint Graph API, webhooks, machine learning operations, and Azure OpenAI is desirable.
Nice to Have
- Prior experience in machine learning operations, Azure Machine Learning, pipelines, and knowledge of LangChain, Vector Storage, and Embedding pipelines is beneficial.
