As Lead Agentic Engineer, you will architect the foundation of our autonomous systems platform. This is not just about writing prompts or experimenting with APIs. It’s about designing durable infrastructure that enables AI agents to reason, plan, use tools, collaborate, and execute complex workflows reliably.

You’ll set technical standards, guide implementation strategy, and mentor other engineers working on agentic systems. The work sits at the frontier of applied AI — translating probabilistic models into structured, dependable operators embedded in real products.

This role combines deep hands-on engineering with architectural leadership. You will shape the long-term direction of how intelligence is deployed across our stack.

What You’ll Do

• Define the architecture for multi-agent systems, orchestration layers, memory frameworks, and tool integrations.

• Lead the design of planning loops, reasoning chains, evaluation pipelines, and reliability safeguards.

• Establish best practices for prompt architecture, model selection, observability, and performance optimization.

• Build scalable backend infrastructure supporting high-throughput agent execution.

• Create evaluation frameworks that measure task success, hallucination rates, cost efficiency, and long-term agent improvement.

• Collaborate cross-functionally with product and leadership to translate strategic goals into technical roadmaps.

• Mentor and review other engineers building agent-based systems.

• Stay ahead of emerging model capabilities and continuously evolve our architecture accordingly.

What We’re Looking For

• Strong experience designing distributed backend systems at scale.

• Deep familiarity with large language models, tool use architectures, retrieval systems, and production deployment.

• Proven ability to take experimental AI workflows and harden them into stable systems.

• Experience leading technical initiatives and influencing architecture decisions.

• Clear communication skills — you can explain complex systems without hiding behind jargon.

• Bias toward execution. Ideas are cheap; reliable systems are rare.

Nice to Have

• Experience with vector databases, embeddings, and large-scale search systems.

• Experience building internal AI platforms or developer tooling.

• Background in ML systems, infrastructure engineering, or applied research.

Why This Role Matters

Autonomous software is still primitive. Most so-called “agents” are brittle wrappers around APIs. We are building something more durable — systems that can reason over context, coordinate tools, recover from failure, and operate with measurable reliability.

You will define that standard here.

Location & Work Style

Remote. Full-time. High ownership. High trust.

Compensation

Competitive salary and meaningful equity aligned with long-term impact.