Description

Key Responsibilities
•    Design and implement AI-powered automation workflows for archiving structured and unstructured data
•    Integrate Claude (Anthropic API) to: 
o    Classify documents
o    Extract metadata
o    Apply retention and compliance logic
•    Build and maintain solutions within Visual Studio / .NET or Python environments
•    Develop prompt engineering strategies to improve accuracy and consistency in classification and tagging
•    Create automation pipelines for ingestion, tagging, storage, and retrieval
•    Collaborate with stakeholders to define archiving rules, taxonomy, and governance models
•    Optimize performance, cost, and latency of LLM-driven processes
•    Implement logging, monitoring, and validation to ensure reliability of outputs
•    Document architecture, workflows, and best practices for handoff

Required Qualifications
•    5+ years of software engineering experience (backend or full-stack with strong backend focus)
•    Hands-on experience working with LLMs (Claude, GPT, or similar) in production environments
•    Strong development experience in Visual Studio (C#/.NET) and/or Python
•    Experience building automation pipelines (APIs, batch processing, event-driven workflows)
•    Solid understanding of: 
o    Data classification and document processing
o    Prompt engineering and LLM evaluation techniques
•    Experience integrating with REST APIs and cloud services (Azure preferred)
•    Ability to work independently in a contract, outcome-driven environment

Preferred / Nice to Have
•    Experience with records management, compliance, or archiving systems
•    Familiarity with vector databases / embeddings for retrieval
•    Exposure to RAG (Retrieval-Augmented Generation) patterns
•    Experience with Azure AI Services or Azure OpenAI
•    Background in building internal tools or enterprise automation platforms

Key Skills

Education

Any Gradute