About the job
We are looking for a seasoned Lead Architect – AI Enablement & Automation (. NET) to spearhead the AI transformation within our client’s engineering organization.
This role merges enterprise-level architectural leadership with hands-on AI automation execution.
The architect will focus on two strategic areas:
- Enablement – Build scalable AI frameworks that empower . NET engineering and QA teams.
- Automation – Create and implement production-ready AI-driven workflows that address significant business challenges.
Key Responsibilities
1. Enablement Pillar – Promoting AI Integration Across Engineering
Enterprise AI Architecture
- Define and establish architectural guidelines for AI integration within . NET 8/Core microservices.
- Set standards for secure, scalable, and cost-effective AI utilization.
Shared AI Infrastructure
- Design and implement a Common AI Service Layer utilizing frameworks like Semantic Kernel or LangChain. NET.
- Develop centralized features including:
- Authentication & secure API access
- Rate limiting & throttling
- Cost tracking & observability
- Model routing & fallback strategies
Developer Acceleration
- Create reusable NuGet packages, SDKs, and frameworks to streamline AI integration.
- Develop project templates and CI/CD pipelines to facilitate the deployment of AI-enabled components.
- Integrate AI best practices into engineering workflows.
Upskilling & Mentorship
- Lead a Community of Practice (CoP) focused on AI integration.
- Mentor C# engineers in:
- Vector search techniques
- Prompt engineering principles
- RAG patterns
- LLM orchestration & tool usage
- Establish technical governance and AI engineering standards.
2. Automation Pillar – Proven AI Delivery at Scale
Agentic Workflow Design
- Architect and implement multi-agent systems that can:
- Execute intricate business logic
- Interface with legacy systems and databases
- Perform autonomous task orchestration
Production-Grade RAG Implementation
- Develop sophisticated Retrieval-Augmented Generation (RAG) systems utilizing:
- Hybrid Search (Vector + Keyword)
- Semantic re-ranking
- Data chunking & partitioning techniques
- Ensure high-accuracy AI-driven support and automation systems.

