AI Engineer - Autonomous Agents Platform

About the role

Feltsense is looking for a hands-on AI Engineer to take ownership of the architecture and development of its autonomous agent system. The company has raised $5.1M to build agents that act as fully autonomous founders, running end-to-end loops from idea to launched product. The role leads the technical direction of the platform, combining architectural decisions with hands-on engineering.

Key responsibilities

• Own the system architecture and make key technical decisions across the platform.
• Design and build multi-agent systems and orchestration infrastructure that take products from idea to launch.
• Develop self-improving agent harnesses, including feedback loops, evaluation systems and memory.
• Build and maintain AI-powered backend services on top of LLM APIs such as Anthropic, OpenAI and Gemini.
• Write production code, especially around agent runtime and orchestration.
• Debug and improve AI behavior in production through prompt engineering, structured outputs, retries and fallbacks.
• Prioritize the engineering roadmap and break down complex challenges into milestones.
• Establish engineering standards around code reviews, testing, observability and releases.
• Lead and support the engineering team while staying deeply involved in implementation.

Required profile

• 4+ years of professional software engineering experience.
• Previous technical leadership experience at an early-stage company (Founding Engineer, Tech Lead, Head of Engineering or similar).
• Experience shipping multi-agent systems and orchestration frameworks to production.
• Experience developing self-improving or self-evolving agent harnesses.

Required skills

• Strong backend engineering, including APIs, services and data flows.
• LLM-based systems: prompt engineering, model configuration, structured outputs, embeddings, retrieval and evaluation.
• Daily hands-on use of AI coding agents such as Claude Code, Cursor or OpenAI Codex, including delegating work and reviewing their output.
• Nice to have: TypeScript and Node.js; Vercel AI SDK, Claude Agent SDK or custom agent runtimes; PostgreSQL, Supabase and pgvector; Inngest or Pub/Sub; Zod, Vitest and GCP Cloud Run; experience growing or restructuring distributed engineering teams.