Staff Software Engineer, AI Platform

Description

About Sapiom

Sapiom is the end-to-end platform that removes barriers to ship and scale agentic products.

We unify what an agent needs to act in the world — compute and sandboxes, memory, identity, spend controls, storage and queues, monitoring — provisioned together as one thing, not handed over as a framework to assemble yourself.

We have assembled a world-class team with deep infrastructure and payments DNA to build the operating system for machines. Our founder ran payments engineering at Shopify for five years and built an autonomous consumer agent company before that. We raised a $35M Series A led by Dragonfly in August, bringing us to $50M total. Accel led our seed; Menlo Ventures and Anthropic are also behind us.

The models are the brain. We're the spine.

About the Role

As a Staff AI Platform Engineer, you'll help define the technical direction of the platform from the ground up. You'll architect distributed systems that power AI agents in production, establish engineering best practices, and partner closely with leadership to shape both the technology and the company.

This is an opportunity to join early and have an outsized impact on the architecture, culture, and product strategy of an AI infrastructure company.

Responsibilities

• Architect the core platform that powers AI agents in production.
• Design distributed systems for agent orchestration, execution, memory, tool calling, workflow coordination, and communication.
• Build reliable infrastructure that enables AI agents to operate safely and efficiently across enterprise environments.
• Lead the technical design of foundational platform capabilities, balancing performance, reliability, extensibility, and developer experience.
• Drive architecture decisions across backend systems, APIs, infrastructure, and AI runtime services.
• Establish engineering standards for scalability, observability, security, and operational excellence.
• Partner with product and engineering leadership to translate emerging AI capabilities into production-ready platform features.
• Mentor engineers through design reviews, technical guidance, and hands-on collaboration.
• Lead complex, cross-functional initiatives from concept through production.
• We're looking for someone who has
• 8+ years of experience building large-scale backend systems, distributed systems, or developer platforms.
• Experience operating technical leadership at the Staff or Principal Engineer level, or demonstrated equivalent scope and impact.
• Strong programming skills in Python, Go, Typescript, or similar languages.
• Experience building developer platforms, SDKs, or API-first products that prioritize reliability, scalability, and developer experience.
• Experience working with modern AI systems, including LLMs, tool calling, structured outputs, retrieval, or agentic workflows.
• Strong systems thinking with the ability to simplify complex technical problems.
• A track record of driving technical strategy while remaining hands-on.
• Experience with event-driven architectures, workflow engines, or distributed execution systems.

Requirements

• Experience building production AI agent platforms or orchestration frameworks.
• Familiarity with LangGraph, OpenAI Agents SDK, CrewAI, AutoGen, Temporal, or similar orchestration technologies.
• Experience with vector databases, retrieval systems, and knowledge infrastructure.
• Experience with LLM serving technologies such as vLLM, SGLang, or TensorRT-LLM.
• Contributions to open-source infrastructure or AI projects.
• Why Sapiom
• We're building the infrastructure that will power the next generation of AI applications.
• Rather than building a single AI product, we're creating the platform developers use to build intelligent, autonomous systems that can coordinate work, integrate with enterprise software, and execute complex workflows reliably.
• As one of the earliest senior engineers, you'll have significant influence over our architecture, engineering culture, and product direction. You'll help define the technical foundation of a company solving some of the hardest problems in production AI.