MLabs is a high-growth, YC-backed company building autonomous AI employees to revolutionize the digital workforce. Their mission is to create full-fledged AI teammates capable of complex tasks, with their first product, Ava, an AI Business Development Representative, already successfully deployed across hundreds of companies. They are dedicated to innovation, high standards, and fostering a collaborative, impact-driven work environment.

About the Position

Introduction

MLabs is building the future of the digital workforce by creating autonomous AI employees that function as full-fledged teammates. Their first AI, Ava, is an AI Business Development Representative (BDR) currently supporting hundreds of companies, handling tasks from lead research to email crafting and meeting bookings autonomously. As the third Applied AI Engineer, you will join a high-growth, YC-backed team (currently at $8M+ ARR) to build the next generation of AI workers, specifically developing "Ava 2.0," a significant advancement in autonomous capability. This role reports directly to the CPTO and offers a direct hand in product direction and the architectural backbone of their agents.

Responsibilities

Model Strategy: Evaluate and select Large Language Models (LLMs), balancing trade-offs between cost, latency, reliability, and accuracy for specific tasks.
Agent Architecture: Design prompt frameworks and agent behaviors for complex workflows, including email generation, web research, and CRM integration.
Workflow Optimization: Build and refine multi-step agent chains using RAG (Retrieval Augmented Generation), web search, and tool-use (calendars, APIs, etc.).
Infrastructure & Safety: Drive choices for orchestration, persistent memory, and "eval loops," while building guardrails to ensure AI safety and trust.
Future Modalities: Explore and deploy emerging technologies, from voice AI to multi-modal reasoning.

Requirements

Experience: 2+ years of experience shipping production-grade AI products, either at an app-layer startup or on a foundation model team.
Technical Depth: Deep hands-on experience with agents, function calling, RAG pipelines, or self-healing workflows (e.g., LangChain, ReAct, OpenAI Tools).
Prompt Engineering: Strong background in prompt design, chaining, and retrieval systems.
Operational Excellence: Proven ability to manage the latency, reliability, and cost of LLM-powered systems in a live environment.
Communication: Excellent verbal and written communication skills with a penchant for directness and candor.
Location: Based in San Francisco, New York, or Remote (USA).

Benefits

Founder Mindset: Empowered to take initiative, challenge ideas, and push for 10x outcomes.
Impact-Driven: Focus on the 80/20 rule, quickly eliminating sunk costs and prioritizing what drives customer value.
High Standards: Attention to detail, from code elegance to product copy quality.
No Drama: A "winning team energy" with low ego, positive vibes, and a genuine love for building.
Growth: Opportunity to work at a fast-scaling startup ($35M+ raised) with a clear path to market leadership in the AI worker space.

About Company

How to Apply

Due to the high volume of applications, individual feedback may not be provided to all candidates. If you do not hear back within 4 weeks, please assume your application was not successful on this occasion. MLabs is committed to equality and accessibility; for any reasonable adjustments or accessible formats, please contact human-resources@mlabs.city. Personal information is collected and processed solely for recruitment purposes in accordance with MLabs Ltd's Privacy Policy.