Lead Systems Engineer - AI

We're building an AI that replaces human coordination in real-world operations. Not chatbots. Not demos. Actual decisions. Actual money. Actual consequences. Our product (REMI) operates inside WhatsApp/SMS and reads messy human conversations, detects operational issues (maintenance, revenue, and inventory), decides what to do, and executes actions with guardrails. We are in internal beta. The system works. Now we need someone to make it reliable, scalable, and production-ready.

Responsibilities:

• You will work directly with the founder to:
• Implement and refine LLM decision pipelines.
• Handle messy, real-world inputs (not clean datasets).
• Improve system reliability (failures, retries, edge cases).
• Ship features quickly without overengineering.
• Review and refine system designs before and after implementation.
• Identify edge cases, failure modes, and incorrect assumptions.
• Improve reliability of real-world workflows (not just correctness in isolation).
• Debug issues across async systems, APIs, and LLM outputs.
• Ensure production-grade behavior from AI-assisted code.

What Makes This Role Challenging:

• Requirements are not always perfectly defined.
• Inputs are messy (human chat, not structured data).
• You will debug edge cases that shouldn't happen.
• You will need to think independently, not just execute tickets.

Within 30 Days:

• Fix 2-3 real issues independently.
• Ship at least one meaningful improvement.
• Reduce founder involvement in debugging.

Within 60 Days:

• Own parts of the system end-to-end.
• Ship without constant supervision.
• Improve system reliability measurably.

Requirements:

• Strong backend experience
• Strong engineering judgment (not just coding ability).
• Ability to spot bad design decisions early.
• Experience working with APIs and asynchronous systems.
• Experience integrating LLMs into real applications (not just prompts).
• Strong debugging skills and independent problem-solving.

Nice to Have:

• Experience with automation systems or bots.
• Experience with production AI systems.
• Startup or 01 product experience.

Tech Stack:

• Node.js backend.
• LLM orchestration (OpenAI / similar).
• Async job processing.

Skills

API, APIs, LLM, OpenAI, async, asynchronous, backend