Lead AI Engineer

We're hiring a Lead AI Engineer to own the design, development, and deployment of production-grade LLM and autonomous agent systems — while also owning the full stack application that delivers them to users. This is a hands-on, high-ownership role for someone who has shipped both AI systems and production software and wants to define technical foundations from the ground up.

You will own core AI architecture decisions, build and maintain our Electron desktop application and its real-time backend, and work closely with leadership on product direction. We're building systems that operate reliably at scale — not demos or experiments, but production software that integrates with professional engineering APIs.

If you've built real LLM systems, understand their failure modes, can architect a full stack application end to end, and want to push agent-based AI into production — this role is for you.

This role is US-based only. We are a fully remote company but only accepting applicants currently residing in the United States.

• Custom code generation agents that understand API semantics and reason about correctness before generating code, including autonomous debugging agents that analyze failures and self-correct
• Multi-agent systems with orchestration patterns, communication protocols, and shared memory for complex multi-step tasks
• Context engineering infrastructure: retrieval systems over technical documentation, context assembly strategies that give LLMs the right information at the right time, and extraction of complex project state
• Model Context Protocol (MCP) servers that expose domain-specific tooling to LLMs
• Evaluation infrastructure — metrics, benchmarks, test harnesses — that drives accuracy from "good enough" to "production reliable"
• Scalable, reliable AI system architectures (inference, orchestration, monitoring)

• An Electron desktop application serving as the primary interface for our AI-powered product
• Real-time communication layers using SSE and WebSockets for streaming responses, live updates, and event-driven UI
• Data engineering pipelines: ingestion, transformation, and storage of domain-specific data, user telemetry, and model performance metrics

Interested in remote work opportunities in Development & Programming? Discover Development & Programming Remote Jobs featuring exclusive positions from top companies that offer flexible work arrangements.

• Python FastAPI backend services including session management, authentication, and integration with the AI orchestration layer
• CI/CD, build tooling, and packaging for cross-platform desktop releases

Strong candidates typically have:

• 9+ years of software engineering experience, with demonstrated depth across the full stack — you're an engineer first, not just an AI specialist
• 3+ years building production LLM systems (not just research or internal demos), with broader AI/ML engineering background
• Strong experience with Electron (or equivalent component-based UI frameworks)
• Production experience with real-time streaming protocols (SSE, WebSockets) for event-driven applications
• Data engineering experience: building pipelines for ingestion, transformation, storage, and retrieval at scale
• Experience building and deploying multi-agent architectures and agentic AI patterns
• Deep expertise in context engineering, RAG, and retrieval systems for code generation use cases
• Deep Python expertise and comfort with complex API integrations (FastAPI, async patterns, subprocess orchestration)
• Ability to reason clearly about tradeoffs (latency, cost, accuracy, reliability)

• Experience building custom code generation agents or AI coding assistants
• Hands-on work with Model Context Protocol (MCP)
• Background in engineering, CAD, or simulation software domains
• LLM fine-tuning experience (RLHF/RLAIF or supervised fine-tuning for code generation)
• Experience designing evaluation frameworks for LLMs and agents

Browse our curated collection of remote jobs across all categories and industries, featuring positions from top companies worldwide.

• Windows desktop application development and packaging (installers, code signing, CI/CD for desktop)
• Contributions to open-source ML/AI tooling or infrastructure
• Prior founding-engineer or early-stage startup experience

We're an early-stage company. There's no playbook, no established processes, and no large team to fall back on. We need someone who thrives in that environment — not someone who tolerates it.

That means:

• You don't wait for specs. You see a gap, you propose a solution, you build it.
• You wear multiple hats. On Monday you're debugging a streaming race condition, on Tuesday you're rearchitecting an agent pipeline, on Wednesday you're reviewing a PR and deploying a hotfix.
• You move fast and ship. You get it working, get it in front of users, and iterate.
• You create structure where none exists. You're comfortable with ambiguity, but you turn chaos into systems rather than letting it persist.
• You want ownership, not just a seat. This isn't a job where you execute someone else's vision — you're shaping the product and the company.
• You've done this before. Prior founding-engineer or early-stage startup experience is a strong signal. You know what "early" really means and you're energized by it.

• Founding-level equity ownership of the company's AI stack and application platform
• Real impact on product direction and system design
• High autonomy and technical decision-making authority
• Competitive salary + equity (range provided during intro call)
• Professional development budget
• High-performance workstation provided
• Remote-first, async-friendly culture