Senior Enterprise AI Platform Engineer

• Designs, builds, and maintains production-grade backend services and APIs (REST) that power agent orchestration, tool execution, and LLM integration for internal automation workflows - with an emphasis on scalability, reliability, and operational readiness.
• Architects and operates MCP server and client infrastructure, including tool registration, enterprise system integration, versioning, and lifecycle management; establishes patterns and standards that the broader team adopts.
• Leads integration of LLM services - streaming, structured outputs, tool/function calling - with robust error handling, retry logic, and cost/latency controls across multi-agent workflows.
• Designs and implements multi-agent and multi-step workflows using orchestration frameworks, evaluating tradeoffs between deterministic, role-based, and autonomous agent patterns.
• Owns observability and reliability for non-deterministic AI systems - defining tracing, monitoring, evaluation frameworks, and cost/latency visibility across the platform.
• Provides technical leadership and mentorship to engineers across the team, conducting code reviews, shaping architectural decisions, and raising the collective engineering bar.
• Partners with architecture, DevOps, and security to define and uphold platform standards for secure, well-tested service delivery following CI/CD and governance best practices.
• Identifies and drives platform improvements proactively, surfacing technical debt, reliability gaps, and architectural risks before they become production issues.
• Uses AI-assisted development - agentic coding, spec-driven development, AI code review - as a core part of how you work, and helps establish adoption norms across the team.

Job Complexity

Having wide-ranging experience, uses professional concepts and company objectives to resolve complex issues in creative and effective ways. Acts as a go-to expert in agent platform infrastructure and AI systems engineering. Some barriers to entry exist at this level (e.g., department and peer review). The level at which a career may plateau for those not pursuing a staff or principal track.

Interaction

Works on complex issues where analysis of situations or data requires an in-depth evaluation of variable factors. Exercises judgment in selecting methods, techniques, and evaluation criteria for obtaining results. Networks with key contacts outside own area of expertise, including architecture, security, and product stakeholders.

Supervision

Determines methods and procedures on new assignments and may coordinate activities of other personnel. Acts as an informal technical lead, providing direction and review within the team without direct managerial authority.

Typically requires a minimum of 8 years of related experience with a Bachelor’s degree; or 6 years and a Master’s degree; or equivalent experience.

Scope

Applies wide-ranging expertise to define platform patterns and standards, resolve complex architectural issues, and influence technical direction across the AI platform. Contributions impact both immediate team output and the longer-term shape of the internal AI platform.

Discretion

Exercises considerable latitude in determining technical objectives and approaches. Errors in judgment may result in significant rework, platform instability, or delays to dependent teams and internal automation programs., * 8+ years of software engineering experience, with a strong track record of shipping and maintaining production backend systems at scale.

• Demonstrated ability to design platform-level systems - not just implement features - including setting standards, patterns, and reusable components that other engineers adopt.
• Proficiency in Python; experience with Node/TypeScript or C# is a plus.
• Solid REST API design experience at scale and deep comfort with relational databases.
• Hands-on experience integrating LLM APIs into real production systems, including building and consuming MCP servers and clients.
• Experience with at least one agent orchestration framework (e.g., LangGraph, CrewAI, AutoGen, Semantic Kernel) and the judgment to evaluate tradeoffs between them.
• Strong understanding of agent design patterns - deterministic workflows vs. role-based vs. autonomous agents - including multi-agent architectures such as supervisor/worker, hierarchical graphs, and ReAct loops.
• Working knowledge of agent-to-agent (A2A) concepts and interoperability patterns.
• Fluent with Docker, Git, and CI/CD; comfortable on the command line and in cloud environments.
• Experience owning observability and evaluation tooling for LLM systems (LangFuse, Prometheus, or similar).
• Sound instincts around secrets management, authentication, and authorization in production AI systems.
• Experience with RAG pipelines and vector databases, including chunking strategies, hybrid search, and re-ranking.
• Familiarity with Azure and Microsoft Entra ID.
• Experience shipping software in a regulated or governed environment (security, privacy, compliance).
• Experience with agentic software development - building with AI coding tools and agent-based workflows as a core part of how you work.

Travel Required

Yes, up to 15% domestic travel may be required.

Work Authorization

Employee must be legally authorized to work in the United States.

isolved is a leading provider of human capital management (HCM) solutions that combines modern technology with expert services and support. Purpose-built for People Heroes , isolved gives HR, payroll and benefits leaders the tools and insights to streamline operations and deliver employee experiences that matter. isolved People Cloud is a connected HCM platform with built-in artificial intelligence (AI) and analytics that brings together HR, payroll, benefits, workforce management and talent management in one experience. Built on a legacy of 40 years in the market, isolved is trusted by more than 200,000 employers and used by 9 million U.S. employees, representing about one in 20 American workers. Visit www.isolvedhcm.com.