AI Engineer Agentic Systems - must be local in Pittsburgh, PA
system one holdingsPittsburgh (PA)
AI Engineer Agentic Systems - must be local in Pittsburgh, PA
Posted 6 days ago
system one holdingsPittsburgh (PA)
SENIORITY
Lead
About the role
AI Engineer, Agentic Systems System One is developing agentic AI tools to automate and modernize its business operations. These agents read documents and records, call business systems and APIs, carry out multi-step workflows, and hand off to people where judgment is needed. The first major project will apply agentic AI to automate a complex enterprise business process, with additional AI solutions to follow. Accuracy, security, and a clear audit trail matter as much as automation.
Role summary:
An engineer with 3 to 6 years of experience who designs, builds, and ships agentic AI tools from requirements to production in Microsoft Azure and System One's enterprise application environment. You will work under the technical direction of an experienced AI architect, who defines the agent architecture and guardrails and reviews your work. This is a hands-on build role with close mentorship. You will own day-to-day technical decisions, the codebase, and delivery.
What you will do:
Turn complex business processes into working agent designs with the architect: agent roles, tool schemas, memory, and human-in-the-loop review points Build production-grade orchestration with LangGraph and Microsoft Agent Framework; integrate tools through MCP and enterprise APIsIntegrate agents with System One business platforms and data flows; enforce output accuracy with validation rules and reconciliation checks Design retrieval over business documents with hybrid search, reranking, metadata filtering, and document-level access control Build and maintain application infrastructure in Microsoft Azure using infrastructure as code and approved CI/CD pipelines, working within established security, identity, and networking standards. Establish LLMOps: automated evaluation suites, guardrails, tracing, and cost and latency budgets Implement security controls: least-privilege identity, secrets handling, audit logging, protection of sensitive business data, and prompt-injection defenses Write design and support documentation, manage work through Azure DevOps Boards, report progress to stakeholders
Required qualifications:
- B.S. in Computer Science, Engineering, or a related field; M.S. preferred3 to 6 years of software, ML, or data engineering experience, with at least 1 year building LLM applications in production
- Expert Python; strong API design and SQL; working familiarity with C#/.NET applications and Microsoft SQL Server/Azure SQLShipped at least one agentic or RAG system to real users
- Experience using AI coding assistants or AI development agents in professional software development, including reviewing, testing, and validating AI-generated code before it is deployed.
- Experience developing and deploying applications in Microsoft Azure, including cloud identity, networking, containers, and serverless technologies
- Experience with infrastructure as code and CI/CD using Azure DevOps or comparable enterprise development practices
- Experience designing evaluation methods for LLM outputs
Preferred qualifications:
- Experience building business automation, financial workflow, or other transaction-oriented enterprise systems
- Multi-agent systems, MCP servers, or custom tool-use frameworks
- Experience integrating workflows and enterprise applications across CRM, ERP, financial, HR/payroll, document management, collaboration, and other SaaS platforms.
- Fine-tuning or serving open-weight models with vLLM, Azure Machine Learning, or approved Azure-hosted services
Certification:
Azure AI App and Agent Developer Associate (AI-103), Azure AI Engineer Associate, Azure Developer Associate, or Azure Solutions Architect Expert
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.