Envision Technology Solutions is seeking a Senior AI Engineer (Pro Code) to design, build, and scale enterprise-grade AI applications. The role involves developing secure, reliable, and observable AI systems that integrate with various business tools and deploying production services on Azure.
Responsibilities:
- Build AI-enabled backend services using C# (.NET 6/7/8) with strong API design, async patterns, resilience, and secure coding practices
- Develop and productionize LLM applications using Azure AI Foundry (prompting, evaluation, telemetry, monitoring, and Responsible AI)
- Implement RAG and Semantic Search systems:
- Embeddings, chunking, metadata design, vector + keyword hybrid search, semantic ranking
- Grounded responses with citations; hallucination reduction techniques
- Integrate with Azure AI Search and/or other vector databases
- Develop and maintain MCP servers for tool-based LLM integration:
- Create tool schemas, manage connectors, enforce authentication/authorization
- Secure integrations with enterprise APIs
- Operate with versioning, monitoring, reliability, and scalable deployments
- Design LLM orchestration workflows:
- Single-agent and multi-agent patterns
- Tool/function calling, structured outputs, prompt templates
- Retries, fallbacks, human-in-the-loop review, caching/token optimization
- Evaluation pipelines and regression testing for prompts/models
- Deploy and run services on Azure App Services (Web Apps/API Apps):
- Networking, authentication, performance, scaling, and observability
- Instrumentation via Azure Monitor / Application Insights
- Collaborate with product, security, and platform teams to ensure compliance, privacy, and Responsible AI implementation
Requirements:
- Design, build, and scale enterprise-grade AI applications using .NET (Backend development)
- Develop secure, reliable, and observable AI systems that integrate with business tools (CRM, ticketing, mailbox, and internal platforms)
- Deploy production services on Azure App Services with modern CI/CD practices
- Build AI-enabled backend services using C# (.NET 6/7/8) with strong API design, async patterns, resilience, and secure coding practices
- Develop and productionize LLM applications using Azure AI Foundry (prompting, evaluation, telemetry, monitoring, and Responsible AI)
- Implement RAG and Semantic Search systems including embeddings, chunking, metadata design, vector + keyword hybrid search, semantic ranking
- Grounded responses with citations; hallucination reduction techniques
- Integrate with Azure AI Search and/or other vector databases
- Develop and maintain MCP servers for tool-based LLM integration including creating tool schemas, managing connectors, enforcing authentication/authorization
- Secure integrations with enterprise APIs
- Operate with versioning, monitoring, reliability, and scalable deployments
- Design LLM orchestration workflows including single-agent and multi-agent patterns, tool/function calling, structured outputs, prompt templates
- Implement retries, fallbacks, human-in-the-loop review, caching/token optimization
- Create evaluation pipelines and regression testing for prompts/models
- Deploy and run services on Azure App Services (Web Apps/API Apps) including networking, authentication, performance, scaling, and observability
- Instrumentation via Azure Monitor / Application Insights
- Collaborate with product, security, and platform teams to ensure compliance, privacy, and Responsible AI implementation