Senior Staff Engineer

Job description:

We are building a shared Agentic AI Platform that enables teams across the enterprise to design, deploy, and operate AI-powered agents and workflows safely, consistently, and at scale.

This role is for a builder-architect, someone with software and systems foundations who can operate hands-on while also shaping architectural direction across teams.

You will design and build core agentic AI platform capabilities while actively ensuring teams adopt shared primitives rather than creating fragmented, one-off solutions.

The role combines hands-on engineering, platform architecture, and cross-enterprise influence, with an emphasis on reuse, cohesion, and long-term sustainability.

This is an individual contributor role (non-managerial).

What you'll do here:

• Design and build foundational platform capabilities for agentic AI systems, including orchestration, lifecycle management, memory patterns, runtime policy, and human-in-the-loop controls.
• Establish agent discovery, registration, and reuse mechanisms (e.g., registries, marketplaces, protocol integration) as shared platform capabilities.
• Define and evolve durable architectural patterns, reference architectures, and golden paths for multi-agent coordination, bounded autonomy, failure handling, and system evolution.
• Design secure-by-default architectures that embed governance, policy enforcement, auditability, and access control into agentic systems and AI workflows.
• Build reusable AI workflow primitives that teams can adopt consistently across the enterprise.
• Partner with enterprise teams (e.g., Cloud, Security, ITSM, etc.) to integrate AI workflows into existing enterprise systems and platforms.
• Maintain a bird's-eye view of Agentic AI and AI workflow initiatives across the enterprise, identifying opportunities to reduce fragmentation and promote convergence.
• Mentor engineers and influence technical direction through hands-on contribution, design leadership, and clear reasoning.

Must have skills:

• 8+ years of experience in designing, building, and operating cloud-native software systems in production environments, with depth in platform, infrastructure, or distributed systems.
• Expertise in tradeoffs across scalability, reliability, security, cost, and developer experience.
• Experience designing or operating systems that incorporate LLMs or AI models as core components, including managing model interaction, control flow, and failure modes.
• Proficiency in Python (and/or Java or Scala) for building backend services, frameworks, or SDKs.
• Experience with public cloud platforms (AWS preferred), including compute, networking, storage, and security primitives.
• Demonstrated experience owning and evolving shared platform architectures over time, including setting boundaries, managing tradeoffs, and adapting designs as scale and requirements change.
• Proven ability to drive architectural alignment across teams through technical influence, design reviews, reference architectures, and hands-on collaboration rather than formal authority.
• Exposure to agent frameworks, multi-agent systems, or AI orchestration tools.
• Experience designing systems with explicit state management, lifecycle control, and correctness guarantees across asynchronous and long-running workflows.
• Experience working with orchestration systems, workflow engines, or event-driven architectures.
• Experience with authentication, authorization, and delegated access patterns, including OAuth 2.0 and related standards, as applied to service-to-service and user-mediated workflows.
• Experience building internal developer platforms, shared services, or reusable runtime frameworks.
• Staying hands-on with emerging AI capabilities and tools that informs system and platform design decisions.

Who Thrives in This Role:

• You think beyond individual teams and care deeply about ecosystem health.
• You enjoy influencing architecture across organizational boundaries.
• You are comfortable operating in designing systems that must evolve.
• You value reuse, cohesion, and long-term sustainability over short-term speed.

Skills

AI Models, AWS, Agent Frameworks, Cloud, Java, LLM, Orchestration, Python, Scala