AI Architect

Core Technical Skills (Must Have)

• 10+ years in software/solution architecture with 2+ years delivering GenAI/LLM solutions in production (adjust as needed).
• Strong knowledge of LLMs: prompting patterns, context windows, tool/function calling, model limitations, and safety risks.
• Agentic AI design experience:
• orchestrators, workflows, multi-step reasoning, tool usage, HITL patterns
• RAG expertise:
• embeddings, vector DBs, hybrid retrieval, reranking, chunking strategies, evaluation
• Cloud architecture (Azure/AWS/GCP) with production engineering rigor:
• microservices, containers (Docker/K8s), serverless, CI/CD
• Solid programming skills (one or more):
• Python, TypeScript/JavaScript, Java, C#
• Experience with APIs and integration patterns:
• REST/gRPC, event-driven systems, queues, workflow engines

Security & Governance (Must Have)

• Understanding of GenAI-specific threats:
• prompt injection, data leakage, jailbreaks, insecure tool calling
• Familiarity with enterprise controls:
• IAM, key management, encryption, network isolation, audit logging
• Responsible AI practices:
• evaluation, content moderation, privacy, and compliance-by-design

Architecture & Systems Skills (Must Have)

• Distributed system design:
• scalability, fault tolerance, caching, performance tuning
• Observability:
• logging/metrics/tracing, prompt/version tracking, monitoring SLIs/SLOs
• Cost management and performance optimization:
• model selection/routing, token reduction, caching, batching

Preferred / Nice-to-Have Skill

• sFine-tuning approaches
• :LoRA/QLoRA, instruction tuning, adapters, distillation (when appropriate
• )Experience with
• :Knowledge graphs, semantic layers, enterprise searc
• hAdvanced evaluation
• :LLM-as-judge with safeguards, rubric scoring, adversarial testin
• gMLOps/LLMOps toolchains
• :experiment tracking, feature stores, model registries, data quality tool
• sDomain experience
• :customer support automation, developer productivity copilots, IT ops agents, finance or healthcare complianc
• eExperience building platforms
• :reusable agent frameworks, reusable RAG components, multi-team enablemen