AI Engineer / AI Agent Engineer

Lab3; United States; Remote; USD 100,000 - 150,000; Full time

Job summary

Lab3 is seeking an AI Engineer / AI Agent Engineer to design, scale, and deploy autonomous AI systems in a fully remote, worldwide setup. You will build RAG pipelines, MCP integrations, and multi-agent orchestration with cross-functional teams to deliver production-grade AI applications.

The ideal candidate has hands-on experience with LLMs, strong software engineering foundations, and a track record of shipping scalable microservices; remote collaboration across time zones is essential.

Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Software Engineering, or related technical discipline.
• 1+ year of professional experience in AI engineering, machine learning development, or advanced software engineering.
• Hands-on practical experience with Large Language Models (LLMs), AI agents, and automated agentic workflows.
• Strong programming proficiency in Python, TypeScript, JavaScript, or Go.
• Solid foundation in software system design, API development, and distributed systems engineering.

Responsibilities

• Design, architect, and deploy next-generation AI systems, autonomous AI agents, and agentic workflows.
• Implement advanced multi-agent orchestration frameworks, reasoning loops, and cooperative task delegation structures.
• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines to enhance context retrieval and reduce hallucinations.
• Build and integrate Model Context Protocol (MCP) servers and clients to connect LLMs with secure enterprise data sources and tools.
• Write clean, maintainable, and high-performance code using Python, TypeScript, JavaScript, or Go.
• Apply strong system design and software engineering principles to build scalable, fault-tolerant distributed AI architectures.
• Conduct rigorous testing, performance profiling, and cost-efficiency optimization for LLM inference and API calls.
• Collaborate with product and engineering teams to define AI roadmaps, evaluate emerging models, and ship new features.
• Maintain comprehensive technical documentation of system architectures, agent prompts, and integration workflows.

Skills

Python

TypeScript

JavaScript

Go

LLMs

Distributed systems

APIs

RAG pipelines

MCP

Remote work

Education

Bachelor's or Master's in CS/AI/SE

Tools

LangChain

AutoGen

CrewAI

LlamaIndex

Docker

Kubernetes

AWS

GCP

Azure

Job description

Position Summary

We are seeking a forward-thinking, highly motivated, and technically proficient AI Engineer / AI Agent Engineer to join our team on a fully remote, worldwide basis. In this cutting-edge artificial intelligence role, you will spearhead the design, development, and deployment of next-generation autonomous AI systems, intelligent agent architectures, and distributed agentic workflows. You will work closely with cross-functional software engineering and research teams to architect robust retrieval-augmented generation (RAG) pipelines, multi-agent orchestration frameworks, and Model Context Protocol (MCP) integrations. Ideal candidates bring a strong foundational background in software systems engineering, hands-on expertise with modern large language models, and a proven passion for building scalable, production-ready AI applications.

Detailed Job Description

As an AI Engineer / AI Agent Engineer at Lab3, you will take full ownership of building, scaling, and optimizing advanced generative AI infrastructure and multi-agent systems. Your day-to-day responsibilities encompass designing autonomous agent loops, executing complex LLM prompt and fine-tuning strategies, and implementing Model Context Protocol (MCP) servers to seamlessly connect AI agents with external tools and data sources. You will write clean, robust code across Python, TypeScript, JavaScript, or Go, ensuring high system reliability, low latency, and efficient token management. Working in a fast-paced remote environment, you will collaborate with peers to translate experimental AI concepts into hardened, production-grade microservices and distributed software solutions.

Key Responsibilities

• Design, architect, and deploy next-generation AI systems, autonomous AI agents, and agentic workflows.
• Implement advanced multi-agent orchestration frameworks, reasoning loops, and cooperative task delegation structures.
• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines to enhance context retrieval and reduce hallucinations.
• Build and integrate Model Context Protocol (MCP) servers and clients to connect LLMs with secure enterprise data sources and tools.
• Write clean, maintainable, and high-performance code using Python, TypeScript, JavaScript, or Go.
• Apply strong system design and software engineering principles to build scalable, fault-tolerant distributed AI architectures.
• Conduct rigorous testing, performance profiling, and cost-efficiency optimization for LLM inference and API calls.
• Collaborate with product and engineering teams to define AI roadmaps, evaluate emerging models, and ship new features.
• Maintain comprehensive technical documentation of system architectures, agent prompts, and integration workflows.

Required Qualifications & Skills

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Software Engineering, or a related technical discipline.
• 1+ year of professional experience in AI engineering, machine learning development, or advanced software engineering.
• Hands-on practical experience working with Large Language Models (LLMs), AI agents, and automated agentic workflows.
• Strong programming proficiency in Python, TypeScript, JavaScript, or Go.
• Solid foundation in software system design, API development, and distributed systems engineering.
• Familiarity with vector databases, embedding generation, and RAG architectural patterns.
• Exceptional problem-solving, analytical, and self-management skills suited for a fully remote, worldwide work environment.
• Excellent written and verbal communication abilities with a strong portfolio or GitHub profile demonstrating real-world AI projects.

Nice-to-Have Skills

• Experience with advanced multi-agent frameworks such as LangChain, AutoGen, CrewAI, or LlamaIndex.
• Familiarity with containerization tools (Docker, Kubernetes) and cloud deployment platforms (AWS, GCP, Azure).
• Practical knowledge of fine-tuning open-source LLMs (Llama, Mistral, Qwen) using PEFT/LoRA techniques.
• Contributions to open-source AI libraries, developer tools, or active participation in technical communities.
• Prior experience scaling production systems in fast-growing tech startups or distributed remote teams.

Application Information

• Salary/Rate: Competitive and commensurate with experience
• Deadline: Open until filled
• Notice Period: Immediate to short notice preferred
• Contract Duration: Permanent / Full-Time (Remote)

Recruitment Pro Tip

When applying for AI agent and LLM engineering roles, ensure your GitHub or portfolio prominently features working code repositories with live agentic loops, custom RAG implementations, or MCP integrations to immediately showcase your practical building capabilities.