Procode Developer (GenAI / LLM Engineer)

Role Overview

The Procode Developer (GenAI / LLM Engineer) will play a critical role in designing, building, and delivering enterprise-grade Generative AI solutions on Microsoft Azure. This role is focused on translating business use cases into secure, scalable, and production-ready AI systems that deliver measurable business value while meeting enterprise governance, security, and compliance standards.

Key Responsibilities

🔹 Enterprise AI Solution Delivery

• Design and implement GenAI solutions using Azure OpenAI and Azure AI Foundry
• Build retrieval-augmented generation (RAG) architectures
• Develop agentic AI systems for enterprise use cases
• Implement prompt engineering, orchestration, and tool/function calling

🔹 Platform & Architecture Enablement

• Design cloud-native, scalable AI architectures on Azure
• Integrate AI services with enterprise systems and data platforms
• Support modernisation and AI platform enablement initiatives

🔹 Governance, Security & Compliance

• Implement responsible AI (RAI) controls and safety guardrails
• Align solutions with enterprise security, compliance, and governance frameworks
• Support model evaluation, monitoring, and auditability

🔹 Delivery & Transformation Support

• Work with client stakeholders across business, IT, and leadership
• Support agile delivery models and enterprise programs
• Enable knowledge transfer, documentation, and internal capability building

Core Capabilities Provided

• GenAI platform engineering
• LLM application development
• Enterprise AI architecture
• Agentic system design
• AI governance & safety
• Cloud-native delivery
• DevOps & MLOps enablement

Technology Landscape

• Languages: Python
• AI Platforms: Azure OpenAI, Azure AI Foundry
• Azure Services: AI Search, Functions, Key Vault, Event Grid, Service Bus, Storage, App Service, Container Apps
• Frameworks: Semantic Kernel, LangGraph, AutoGen
• DevOps: Git, CI/CD, Observability (App Insights, Log Analytics)
• Data: Vector DBs, embeddings, RAG pipelines

Engagement Outcomes

• Production-ready AI solutions
• Secure enterprise AI platform
• Scalable AI architecture
• Measurable business value
• Accelerated AI adoption
• Sustainable internal capability