Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Franklin Fitch

NewBe an early applicant

Software Engineer - AI

Posted

Description

Senior Agentic AI Engineer (Full-Stack) | Azure, .NET, Angular


Senior Agentic AI Engineer to build agentic products that run in real customer environments. If you have shipped multi-agent workflows to production and you measure yourself on latency, token cost, reliability and security, read on.


The role


You will own agentic features end to end, from orchestration logic to the operator UI that customers use to supervise it.


  • Build multi-agent workflows with AutoGen and Semantic Kernel, grounded with Azure OpenAI and Azure AI Search
  • Write the .NET Core/C# services and tool APIs the agents depend on
  • Build Angular/TypeScript operator dashboards with human-in-the-loop controls and full audit visibility
  • Own delivery from R&D through to stable production, including observability and cost control
  • Treat security as engineering, not paperwork: PII-safe prompt handling, output validation, data minimisation and safe function calling, all written as code and tests from the first commit


What you bring


Essential:


  • Production experience with AutoGen or Semantic Kernel (both is a strong plus), including tool and function implementation
  • Azure OpenAI and Azure AI Search in production, covering retrieval and function-calling patterns
  • Strong .NET Core/C# and Angular/TypeScript
  • Evidence of improving latency, cost and reliability with numbers, on systems that were instrumented and maintainable


Nice to have:


  • CrewAI, LangGraph or LangChain
  • MCP servers, both building and consuming
  • Experiment tracking and A/B evaluation for LLM features
  • Experience with models beyond OpenAI (Claude, Gemini, Llama, Mistral)


The stack


AutoGen, Semantic Kernel, Azure OpenAI, Azure AI Search, .NET Core/C#, Angular/TypeScript, Azure API Management, SQL Server, Cosmos DB, AKS, Azure DevOps, GitHub Actions, Application Insights, Prometheus/Grafana


What success looks like


  • First 8 to 12 weeks: an agentic workflow live in production, meeting agreed p50/p95 latency and per-task token cost budgets
  • By 180 days: rising tool-use success and evaluation pass rates, zero PII leakage in tests, and guardrails documented and enforced in code


Skills

Apply

See also

Software Engineering jobs by country — openings, pay and top skills →