Description

Audit SDLC workflows to identify AI integration opportunities and build reusable AI tools, scripts, and agent-based systems.

This role is on-site.

Responsibilities

• Audit planning, development, code review, testing, and deployment workflows to map high-ROI AI integration points.
• Design and develop internal tools and LLM-powered integrations using Python and Docker.
• Build and deploy autonomous multi-agent workflows using LangGraph, LangChain, or AutoGen.
• Manage LLMOps lifecycle including prompt versioning, output monitoring, cost tracking, and agent observability.
• Design AI guardrails, run evaluations for quality and safety, and integrate AI coding assistants into daily engineering practices.

Required Skills

• 6–8 years of hands-on software development experience with strong SDLC fundamentals.
• Proficiency in Python with familiarity in .NET or TypeScript.
• Experience with LLM APIs (OpenAI, Azure OpenAI, Anthropic) and structured prompt engineering.
• Practical knowledge of agentic AI frameworks such as LangGraph, LangChain, AutoGen, or CrewAI.
• DevOps awareness including CI/CD pipelines, Docker, and enterprise Git workflows (GitHub, Azure DevOps, GitLab).
• Experience with AI evaluations, guardrail design, and hallucination detection.
• Hands-on use of AI coding assistants like GitHub Copilot or Cursor.

Preferred Skills

• Experience building internal AI-powered developer tools or working in an AI CoE.
• Familiarity with AI observability platforms such as LangSmith, AgentOps, Arize, or Helicone.
• Exposure to Azure AI Foundry or Azure Document Intelligence.

Key Skills

Education

Bachelor's degree