Staff Engineer, AI

THE OPPORTUNITY

At Sema4.ai http://Sema4.ai, we’re building an Enterprise AI Agent platform that fundamentally changes how knowledge work gets done—by enabling people and AI agents to collaborate in durable, trustworthy ways.

As a Staff Engineer on the AI team, you’ll design, build, and extend Sema4.ai http://Sema4.ai’s cognitive architectures—the core platform at the center of our agents. You’ll blend cutting-edge AI research with production-grade rigor to deliver high-leverage capabilities to the agents our customers build daily.

This is an early, high-impact role. You’ll be building foundational infrastructure in a fast-moving environment where decisions matter and tradeoffs are real. We’re looking for engineers who are comfortable operating with ambiguity, but who bring rigor, taste, and strong technical judgment to everything they build.

WHO YOU ARE

GenAI Expert

You know how to make LLMs and agents do real work in production systems. You understand the sharp edges: prompt brittleness, context limits, tool failures, cost and latency constraints, provider quirks, and enterprise reliability requirements. You’re fluent in current approaches used in AI systems development, and you know how to apply them thoughtfully rather than reflexively.

In-depth Technologist

You stay close to research and industry, but you don’t chase every new idea. You track where the field is heading and design systems that will adapt gracefully as models and techniques evolve. You evaluate trends critically, adopt what works, and avoid unnecessary complexity. You think carefully about abstraction boundaries, failure modes, and long-term maintainability.

Builder With Standards

You care about correctness, clarity, and operational behavior. You’re comfortable iterating quickly, but you understand the limits of your systems and know how to address them when the time is right. You know how to navigate between “not invented here” syndrome and assuming someone else has already solved all your problems.

WHAT YOU’LL DO

Build and Own Core Systems

You’ll spend most of your time developing and evolving core agent framework components, orchestration logic, and LLM integration layers. These are not experiments; they are systems customers will rely on for business-critical workloads, and you’ll own them end to end.

Work Close to the Product

Collaborate directly with the product and field engineering teams to understand how customers are building and applying agents. You’ll help translate these product intents into robust systems, and design new capabilities to advance the art of the possible.

Solve Ambiguous, High-Leverage Problems

Take on problems where the shape of the solution isn’t obvious: improving agent reliability, managing long-running workflows, balancing cost and performance, and integrating new model capabilities responsibly. You’ll be trusted to figure things out, from concept to production.

Contribute to Technical Culture

You’ll participate actively in design reviews and code reviews, help shape technical standards, and interview technical candidates. You’ll lead with influence across the engineering and product teams.

WHAT YOU BRING

• 7+ years of software engineering experience, including 2+ years building AI/ML systems in production
• Deep experience with backend systems in Python, including performance, observability, and reliability concerns
• Hands-on experience designing and operating LLM-based systems (agents, orchestration, retrieval, tools, etc.)
• Strong communication skills: whether you’re talking to colleagues, customers, or machines, you communicate clearly, concisely, and collaboratively
• A high-ownership mindset: you care deeply about the systems you build, and you take responsibility for their long-term health