AI Engineer VS Code

We are seeking an AI Engineer to design, develop, and evolve the VZ Application AI Modernization Factory
—an AI-powered platform that automates and accelerates the modernization of large-scale enterprise legacy applications.

This VS Code extension-based solution leverages Large Language Models (LLMs), knowledge graphs, adaptive questioning, and automated code generation to transform legacy Java/Oracle systems into modern architectures such as NSA.

The role involves driving the end-to-end technical vision of the AI Factory—from intelligent source code analysis to automated artifact generation—while collaborating closely with modernization teams, platform engineers, and AI specialists to continuously improve throughput, accuracy, and coverage.

• Implement a prompt engineering system using structured YAML and Markdown templates
  , including:
• Dynamic placeholder substitution
• Priority filtering
• Category-based routing
• Multi-instance Light
  
  RAG targeting
• Build and enhance the Adaptive Questioning Framework
  , featuring:
• Configurable probing depth and levels
• Migration-critical validation guarantees
• Implement and maintain MCP server integrations
  , including:
• Vector store operations (upsert, search)

• Design, build, and maintain a VS Code extension (Type Script/Node.js), including:
• Chat participant integration
• Command handlers
• Guided conversational workflows
• Design and implement a multi-stage modernization pipeline
  :
• Application selection
• Module-level targeted analysis
• Develop and evolve a modular extension architecture
  , including:
• Handlers
  :
  Chat participant, conversations, APIs, workflows
• UI components
  :
  Buttons, markdown rendering, progress indicators
• Implement a tiered error-handling framework
  :
• Early-stage failure
  :
  Stop execution and prompt connectivity diagnostics
• Mid-stage failure
  :
  Pause and auto-retry with exponential backoff
• Late-stage failure
  :
  Continue with partial results
• Error classification: NETWORK, AUTH, SERVER, TIMEOUT, UNKNOWN
• Maintain build and packaging pipelines
  , including:
• Type Script strict compilation
• Automated VSIX packaging
• Integrate the VS Code extension with Light
  
  RAG services
  , including:
• Endpoint targeting and routing
• Contextual retrieval of legacy code artifacts
• Collaborate with:
• Light
  
  RAG platform teams on ingestion pipelines and retrieval quality
• AI engineering peers on shared architecture and enhancements

• Maintain Python-based services for vector operations
  , including:
• Cosine similarity
• Batch similarity computation
• JSON-based Type Script Python subprocess interoperability
• Automatic Type Script fallback on failures
• External embedding API integrations
• Batch processing
• Exponential backoff retry strategies
• Configurable batching

• Prompt Engineering System
• YAML/Markdown-based prompt loader with dynamic filtering, substitutions, and routing
• AI Chat Agent
• VS Code chat participant enabling guided modernization workflows
• Recursive LLM-driven analysis with depth control and migration enforcement
• Knowledge Graph Integration
• Light
  
  RAG + Neo4j pipeline for context-aware analysis
• Artifact Generation Pipeline
• Automated generation of:
• Low-Level Designs (LLD)
• Code instructions
• Test instructions
• MCP Server & Tools
• Integration with vector stores, graph databases, and file metadata services
• Late Chunking & Embedding
• Efficient semantic retrieval to optimize token usage
• Python Vector Services
• High-performance similarity and embedding computation