Senior DevOps Engineer

SEI•Upper Providence Township, PA

2d•Hybrid

About The Position

SEI is looking for a Senior DevOps Engineer to join our Enterprise AI team. This role is about building and operating reliable cloud‑based systems by writing code, automating infrastructure and delivery workflows, and reducing friction for developers and users. You will work closely with InfoSec, Cloud engineers and business stakeholders to design, deploy, and operate systems with clear ownership and practical engineering judgment. We expect you to use modern tooling, including AI‑assisted tools where appropriate, to speed up automation, troubleshooting, and operations while remaining accountable for correctness, security, and reliability.

Requirements

BA/BS, in a related technical field; or the equivalent in education and work experience
Minimum of 8 years prior work experience with software/ML engineering
Strong Python (APIs, services, production)
Deep RAG expertise: embeddings, hybrid search, chunking, reranking, evals, guardrails.
Agentic AI: multi‑step agents, tool calling, orchestration frameworks (LangChain/LlamaIndex or custom).
MCP / plugin patterns, tool‑server integration, context protocol design.
Azure: OpenAI/Models, AI Search, ML, AKS, Functions, Key Vault, VNET/private endpoints.
Solid grasp of LLM lifecycle: prompting, structured outputs, token/cost management, fine‑tuning concepts.
Ability to design for regulated industries: PII handling, isolation, audit, governance readiness.

Nice To Haves

LLM fine‑tuning (LoRA/QLoRA), evaluation frameworks (RAGAS, pairwise).
Vector databases (Milvus, Pinecone, Weaviate).
TrustAI implementation: safety evals, governance dashboards, drift monitoring.
TypeScript/Node for plugins or front‑end integrations.
Ability to clearly communicate both verbally and in writing with client and team members, including experience documenting and presenting findings
Excellent analytical skills, organizational abilities, and problem-solving skills
Self-starter who works efficiently in a fast-paced environment with changing priorities and a geographically distributed team
Ability to think creatively and seek optimum solutions
Ability to grasp loosely defined concepts and transform them into tangible results and key deliverables
Diagnostic skills with the ability to analyze technical, business and financial issues and options
Ability to infer from previous examples, willingness to understand how an application is put together
Action-oriented, with the ability to quickly deal with change

Responsibilities

Design AI architectures end‑to‑end: 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: build rapid POCs in Python to validate architecture, derisk decisions, and accelerate delivery.
Drive TrustAI: hallucination testing, bias/fairness evals, lineage, scoring, drift monitoring, and compliance alignment.
Design robust telemetry: retrieval/prompt tracing, eval feedback loops, guardrail instrumentation (OpenTelemetry, Langfuse, App Insights).
Interface with InfoSec & Cloud Enablement: private networking, identity boundaries, policy‑as‑code, DLP, model‑risk governance.
Publish reference architectures, reusable modules, decision playbooks; lead design reviews and mentor engineers.