Senior Enterprise AI Platform Engineer

isolved•,

About The Position

The Senior Enterprise AI Platform Engineer is a senior individual-contributor and builder role focused on production internal systems, rather than model training, research, or customer-facing product features. The role designs and implements platform components for agents and internal tools, makes architectural decisions, establishes platform standards, and mentors peers. The engineer helps build internal platforms that enable teams across the company to automate work and processes, while shaping engineering practices and owning the reliability and scalability of what is delivered. The role focuses on production-grade backend services and APIs for agent orchestration, tool execution, and LLM integration. It includes architecting MCP infrastructure, integrating LLM services and orchestration frameworks, and owning observability and reliability for non-deterministic AI systems. The position provides technical leadership without direct managerial authority and partners with architecture, DevOps, and security to uphold platform standards and governance practices. The position may require up to 15% domestic travel. The employee must be legally authorized to work in the United States. The role is classified as exempt and may be office, hybrid, or remote.

Requirements

At least 8 years of software engineering experience with a strong track record of shipping and maintaining production backend systems at scale; the experience section also states typically 8 years with a bachelor's degree, 6 years with a master's degree, or equivalent experience.
Demonstrated ability to design platform-level systems and establish standards, patterns, and reusable components adopted by other engineers.
Proficiency in Python.
Solid REST API design experience at scale and deep comfort with relational databases.
Hands-on experience integrating LLM APIs into production systems, including building and consuming MCP servers and clients.
Experience with at least one agent orchestration framework, such as LangGraph, CrewAI, AutoGen, or Semantic Kernel, and the judgment to evaluate tradeoffs among them.
Strong understanding of agent design patterns, including deterministic workflows, role-based and autonomous agents, and multi-agent architectures such as supervisor/worker, hierarchical graphs, and ReAct loops.
Working knowledge of agent-to-agent (A2A) concepts and interoperability patterns.
Fluency with Docker, Git, and CI/CD; comfort with command-line work and cloud environments.
Experience owning observability and evaluation tooling for LLM systems, such as LangFuse or Prometheus.
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.
Experience shipping software in a regulated or governed environment involving security, privacy, or compliance.
Experience with agentic software development, including using AI coding tools and agent-based workflows as a core part of work.
Legally authorized to work in the United States.

Nice To Haves

Experience with Node/TypeScript or C#.
Familiarity with Azure and Microsoft Entra ID.

Responsibilities

Design, build, and maintain production-grade backend services and REST APIs for agent orchestration, tool execution, and LLM integration in internal automation workflows.
Architect and operate MCP server and client infrastructure, including tool registration, enterprise system integration, versioning, and lifecycle management; establish patterns and standards for the broader team.
Lead integration of LLM services, including streaming, structured outputs, and tool/function calling, with robust error handling, retry logic, and cost and latency controls across multi-agent workflows.
Design and implement multi-agent and multi-step workflows using orchestration frameworks, evaluating deterministic, role-based, and autonomous agent patterns.
Own observability and reliability for non-deterministic AI systems by defining tracing, monitoring, evaluation frameworks, and platform cost and latency visibility.
Provide technical leadership and mentorship, conduct code reviews, shape architectural decisions, and raise the team's engineering standards.
Partner with architecture, DevOps, and security to define and uphold platform standards for secure, well-tested service delivery, CI/CD, and governance.
Proactively identify and drive platform improvements, addressing technical debt, reliability gaps, and architectural risks.
Use AI-assisted development, including agentic coding, spec-driven development, and AI code review, and help establish adoption norms across the team.
Determine methods and procedures for new assignments and may coordinate other personnel's activities; provide informal technical direction and review without direct managerial authority.