Feltsense AI Engineer

VettedBench; United States; Remote; USD 150,000 - 210,000; Full time

Job summary

VettedBench is seeking a hands-on AI Engineer to own the architecture and development of our autonomous agent system. You will lead technical direction, build multi-agent orchestration, and ship production code while shaping engineering standards as the company scales.

You'll work across backend services leveraging LLM APIs such as Anthropic, OpenAI, and Gemini, and develop self-improving agent harnesses with a focus on reliability and observability.

Qualifications

• 4+ years of professional software engineering experience.
• Leadership roles at early-stage startups (Founding Engineer / Tech Lead).
• Hands-on production experience with multi-agent systems and orchestration.
• Experience with LLM-based systems and prompt engineering.
• Strong backend API and data-flow design skills.
• Experience with AI coding agents (Claude Code, Cursor, Codex).

Responsibilities

• Own system architecture and key technical decisions across the platform.
• Design and build multi-agent orchestration infra that takes products from idea to launch.
• Develop self-improving agent harnesses with feedback loops and memory.
• Build AI-powered backend services on top of LLM APIs (Anthropic, OpenAI, Gemini).
• Write production code for agent runtime and orchestration.
• Improve AI behavior in production through prompt engineering, structured outputs, retries, and fallbacks.
• Lead and mentor the engineering team while shaping the road map and standards.

Skills

Technical leadership

Multi-agent systems

Backend design & APIs

LLM-based systems

Prompt engineering

Tools

TypeScript

Node.js

Vercel AI SDK

Claude Agent SDK

OpenAI Codex

PostgreSQL

Supabase

pgvector

Inngest

Pub/Sub

Zod

Vitest

GCP Cloud Run

Job description

About the company

We raised $5.1M to build agents that operate as fully autonomous founders. Our backers include Matt Schlicht (founder of Moltbook), the founders of Crunchbase and Republic, and VCs including Draper, Precursor, and Liquid2. We're working at the frontier of autonomous systems, building agents that don't just chat, but run entire businesses. Our system identifies business opportunities through market signals, validates ideas with live ad tests, builds and launches software products, and brings in human experts wherever agents fall short. That loop already runs end to end: from idea to launched product to first revenue. Over the next 12 months, our focus is on reliability, throughput, and self-improvement, making every launch better than the last.

About the role

We're looking for a hands-on AI Engineer to take ownership of the architecture and development of our autonomous agent system. You'll lead the technical direction of the platform, building multi-agent orchestration systems, self-improving agent harnesses, and AI-powered backend services. This is a highly technical leadership role that combines architectural decision-making with hands-on engineering. You'll be expected to ship production code, make key technical decisions, improve agent behavior in production, and help establish the engineering standards as the company scales.

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, particularly around agent runtime and orchestration.
• Debug and improve AI behavior in production through prompt engineering, structured outputs, retries, and fallbacks.
• Break down complex technical challenges into actionable milestones and prioritize the engineering roadmap.
• Establish engineering standards around code reviews, testing, observability, and release processes.
• Lead and support the engineering team while remaining deeply involved in implementation.

Requirements

• 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).
• Hands-on experience building and shipping multi-agent systems and orchestration frameworks to production.
• Experience developing self-improving or self-evolving agent harnesses.
• Strong backend engineering skills, including designing and maintaining APIs, services, and data flows.
• Experience working with LLM-based systems, including prompt engineering, model configuration, structured outputs, embeddings, retrieval, and evaluation.
• Daily hands-on experience with AI coding agents such as Claude Code, Cursor, OpenAI Codex, or similar tools. You should know how to delegate work to agents, review their output, and verify what they build.

Nice to have

• Strong TypeScript and Node.js experience.
• Experience with Vercel AI SDK, Claude Agent SDK, or building custom agent runtimes.
• Experience with PostgreSQL, Supabase, and pgvector.
• Familiarity with background job systems such as Inngest or Pub/Sub.
• Experience with Zod, Vitest, and GCP Cloud Run.
• Experience growing or restructuring distributed engineering teams.
• Interest in AI evaluation, safety, and observability.