AI Architect

Job Overview

SEI is seeking an AI Architect to design and deliver enterprise AI platforms—RAG systems, agentic frameworks, document intelligence services, and responsible‑AI patterns—on Azure. The role bridges strategy and execution, defining reference architectures, running fast POCs, writing production code, and partnering with Info Sec, Cloud, and business stakeholders.

• Design AI architectures end-to-end, including RAG pipelines, agentic orchestration (multi‑agent, tool use, MCP), retrieval strategies, grounding, and structured outputs.
• Architect Document Intelligence as a Service: ingestion, OCR/vision, extraction, verification, multi‑tenant design, and sensitive‑data handling.
• Define enterprise patterns: prompt governance, model routing, security envelopes, HITL gates, plugin/MCP integration, fallback/verification flows.
• Prototype fast POCs in Python to validate architecture, derisk decisions, and accelerate delivery.
• Drive Trust
  
  AI: hallucination testing, bias/fairness evaluations, lineage, scoring, drift monitoring, and compliance alignment.
• Design robust telemetry: retrieval/prompt tracing, evaluation feedback loops, guardrail instrumentation (Open Telemetry, Langfuse, App Insights).
• Interface with Info Sec & Cloud Enablement on private networking, identity boundaries, policy‑as‑code, DLP, and model‑risk governance.
• Publish reference architectures, reusable modules, and decision playbooks; lead design reviews and mentor engineers.

• Minimum 10 years of experience in software/ML engineering.
• Strong Python proficiency (APIs, services, production).
• Deep RAG expertise: embeddings, hybrid search, chunking, reranking, evaluations, guardrails.
• Experience with Agentic AI: multi‑step agents, tool calling, orchestration frameworks (Lang Chain, Llama Index or custom).
• Knowledge of MCP/plugin patterns, tool‑server integration, and context protocol design.
• Hands‑on experience with Azure services (OpenAI/Models, AI Search, ML, AKS, Functions, Key Vault, VNET/private endpoints).
• Understanding of the LLM lifecycle: prompting, structured outputs, token/cost management, fine‑tuning concepts.
• Ability to design for regulated industries: PII handling, isolation, audit, governance readiness.
• Excellent communication skills, able to present to C‑suite, Info Sec, and engineering audiences.

• Experience working with large application development teams and delivery managers in heterogeneous environments.
• Experience engaging with senior leadership.
• LLM fine‑tuning (LoRA/QLoRA), evaluation frameworks (RAGAS, pairwise).
• Vector database expertise (Milvus, Pinecone, Weaviate).
• Trust
  
  AI implementation: safety evaluations, governance dashboards, drift monitoring.
• Type Script/Node for plugins or front‑end integrations.

The role offers a hybrid schedule, working 3 days in the office. Benefits include comprehensive healthcare (medical, dental, vision, prescription, wellness, EAP, FSA), life and disability insurance, a 401(k) match, education assistance, commuter benefits, paid holidays, PTO, paid parental leave, backup childcare arrangements, paid volunteer days, a discounted stock purchase plan, investment options, and access to employee networks.

SEI is an Equal Opportunity Employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability status, protected veteran status, or any other characteristic protected by law.