Lead Principal Engineer, Enterprise Agentic AI Platform

Description

The Enterprise AI & Automation team in the company IT is building and extending enterprise-grade agentic AI systems. The company is one of the leading AI companies in the world.

The company's Enterprise AI Platform runs production AI agents that connect securely to enterprise systems. They raise employee productivity and speed up business outcomes in engineering, IT, supply chain, finance, HR and sales.

The team wants a Principal or Distinguished Engineer level architect who shapes systems by building them. This is a hands-on technical leadership role where you write Python and/or Go code every day. You build quick prototypes with modern code generation tools such as Cursor, Claude Code and Claude Cowork.

You need a working grasp of infrastructure, from Kubernetes to GPU inference stacks, and you turn new agent development patterns into scalable platform features. You will define the agent architecture by shipping working systems, writing reference implementations and raising technical standards across the organization.

This is not a strategy or governance role. Architectural authority comes from production systems, measurable results and deep technical skill.

The role suits someone who works well with ambiguity, moves quickly from concept to running system, and cares about the full agent lifecycle: create, sandbox, launch, observe, control and keep improving through data-driven cycles. You will design systems with persistent memory, controlled runtimes, rigorous assessment and GPU-backed performance, so agents are intelligent, traceable, protected and production-ready from the start.

Responsibilities

• Build and ship production-grade agentic AI systems end to end in Python and/or Go, covering Kubernetes deployment, agent runtimes, memory, orchestration, tool integration and evaluation pipelines.
• Define and evolve the company's enterprise agentic AI architecture through working implementations, reference systems and production deployments rather than abstract diagrams.
• Design and build multi-agent orchestration patterns such as planner, executor, reviewer and tool agents, using LangChain, LangGraph or similar frameworks, with solid regression coverage and observability.
• Run fast, rigorous proofs of concept on emerging agent architectures, then turn the patterns that work into reusable platform services, APIs, SDKs and developer templates.
• Build data flywheels that steadily improve agent quality through telemetry, benchmarking, automated evaluation and structured feedback.
• Build security, guardrails, sandbox isolation, auditability and policy enforcement into agent runtimes, working with security and governance teams.
• Assess, integrate and extend open-source and third-party agent platforms, and make build-or-buy decisions based on performance, scalability, control and long-term ownership.
• Work with engineering, infrastructure, product and business partners to align architecture with enterprise priorities and speed up adoption.

Requirements

• A bachelor's degree in Computer Science or a related field, or equivalent experience. A master's or PhD is preferred.
• 15+ years building and shipping large-scale distributed systems, with extensive hands-on coding in Python, Go or a similar systems language.
• A proven record of moving from an idea to a working prototype, then to a robust, scalable platform.
• A proven record building agentic AI systems, including RAG pipelines, long-lived memory models, multi-agent management (for example LangChain or LangGraph), tool frameworks and evaluation infrastructure.
• Expert knowledge of Kubernetes, containerized workloads, networking, APIs and secure enterprise integration patterns.
• Experience building benchmarking, regression testing, telemetry and observability systems that measure agent quality, latency, cost, reliability and safety.
• Thorough knowledge of performance tuning in hybrid environments, including GPU-based inference.
• Strong collaboration skills. You can influence cross-functional partners and explain complex architecture clearly to both technical and business audiences.
• Nice to have: experience delivering reusable developer tooling such as SDKs, APIs, templates, reference implementations and CI/CD automation.
• Nice to have: experience integrating enterprise vector databases and retrieval systems, and working with agentic search and orchestration platforms such as Glean, Microsoft Copilot Studio, Google Agentspace or similar enterprise AI ecosystems.
• Nice to have: experience adding fine-grained policy enforcement, access controls, sandbox isolation and audit trails directly into AI runtimes.
• Nice to have: experience optimizing model inference, batching and memory use on the company hardware.
• Nice to have: meaningful open-source contributions, such as core commits, maintainership, widely adopted libraries or public technical work showing system-level depth.

Conditions

Applications are accepted until at least November 3, 2026.

This posting is for an existing vacancy.

The company uses AI tools in its recruiting process.

The expected base salary is 272,000 USD to 431,250 USD, set by location, experience and other objective job-related factors.

The company is an equal opportunity employer and does not discriminate on the basis of any legally protected characteristic.