We are seeking a highly experienced Lead Architect – AI Enablement & Automation (.NET) to drive the AI transformation of our client’s engineering organization.
This role combines enterprise-level architectural leadership with hands-on AI automation delivery.
The architect will operate across two strategic pillars:
- Enablement – Establish scalable AI foundations that empower .NET engineering and QA teams.
- Automation – Design and deploy production-grade AI-driven agentic workflows solving high-value business problems.
Key Responsibilities
1. Enablement Pillar – Scaling AI Adoption Across Engineering
Enterprise AI Architecture
- Define and implement architectural guardrails for AI integration within .NET 8/Core microservices.
- Establish standards for secure, scalable, and cost-efficient AI consumption.
Shared AI Infrastructure
- Design and develop a Common AI Service Layer using frameworks such as Semantic Kernel or LangChain.NET.
- Implement centralized capabilities including:
- Authentication & secure API access
- Rate limiting & throttling
- Cost tracking & observability
- Model routing & fallback strategies
Developer Acceleration
- Build reusable NuGet packages, SDKs, and frameworks to standardize AI integration.
- Create project templates and CI/CD pipelines enabling teams to deploy AI-enabled modules as easily as standard Web APIs.
- Embed AI best practices into engineering workflows.
Upskilling & Mentorship
- Lead a Community of Practice (CoP) for AI adoption.
- Mentor C# engineers in:
- Vector search concepts
- Prompt engineering
- RAG patterns
- LLM orchestration & tool usage
- Drive technical governance and AI engineering standards.
2. Automation Pillar – Proven AI Delivery at Scale
Agentic Workflow Design
- Architect and implement multi-agent systems capable of:
- Executing complex business logic
- Interacting with legacy systems and databases
- Performing autonomous task orchestration
Production-Grade RAG Implementation
- Build advanced Retrieval-Augmented Generation (RAG) systems using:
- Hybrid Search (Vector + Keyword)
- Semantic re-ranking
- Data chunking & partitioning strategies
- Deliver high-accuracy AI-driven support and automation systems.
AI Reliability & Operational Excellence
- Implement enterprise-grade reliability mechanisms:
- Retry policies
- Fallback models (e.g., GPT-4 → Phi-3 or equivalent)
- Hallucination detection & validation frameworks
- Define observability standards for latency, cost, and accuracy.
Performance & Cost Optimization
- Optimize token consumption and inference latency.
- Implement semantic caching strategies.
- Tune memory and concurrency management within the .NET runtime.