AI Software Engineer

Job Description

AI Software Engineer:

• Own the end-to-end architecture of the AI-assisted migration platform — agent/skill/harness design, AI-in-the-loop bounding of LLM output, and Azure cloud architecture (App Services, Functions, Key Vault, Azure AD).
• Drive AI/ML strategy: build-vs-buy and model selection calls, fine-tuning vs. prompting and cost/latency trade-offs, and definition of fidelity scoring and gap-analysis evaluation metrics.
• Lead delivery and stakeholder management — scope feasibility studies vs. production builds, define data requirements with customer IT teams, and triage client edge-case escalations into a prioritised backlog.
• Lead and mentor a 3–8 person AI/automation engineering team across classical and prompt-engineering disciplines, while owning migration risk, rollback strategy, and security/credential review.
• Develop AI/LLM components — prompt engineering with schema-constrained output, LLM API integration (Anthropic/OpenAI/Azure OpenAI), and RAG or classification pipelines that map legacy actions to modern equivalents.
• Integrate the solution with the surrounding ecosystem via REST APIs, webhooks, Azure CLI/Azure AD authentication flows, and MCP server endpoints.
• Own quality through automated workflow validation tests and eval harnesses that score model output fidelity, and document unsupported or manually reviewed conversion cases.
• Build and maintain the parsing/conversion engine (Node.js/TypeScript or Python) that reads XML/JSON-based Nintex workflow definitions and generates equivalent Power Automate flow logic.

AI Developing Skill

Skills:

• Core Programming & Parsing - Node.js / TypeScript or Python (framework matching the Agent's stack)
• Core Programming & Parsing - XML/JSON parsing experience (Nintex NWF is XML-based)
• Core Programming & Parsing - Experience building parsers, ASTs, or rule engines
• Core Programming & Parsing - Regex / expression-language conversion experience
• AI / LLM Engineering - Prompt engineering / structured (schema-constrained) output generation
• AI / LLM Engineering - LLM API integration (Anthropic, OpenAI, Azure OpenAI)
• AI / LLM Engineering - RAG or classification pipeline experience
• AI / LLM Engineering - Coding Agent experience via Claude / Github copilot
• AI / LLM Engineering - Eval-harness / model output scoring experience
• Integration / Ecosystem - MCP (Model Context Protocol) server development
• Integration / Ecosystem - Azure CLI / Azure AD authentication flows
• Integration / Ecosystem - REST API integration & webhook handling
• Testing & Quality - Test automation for workflow/flow validation
• Testing & Quality - Application level testing best practices
• Nice to Have (General) - SharePoint / M365 admin experience