year

24-Mag•New York, NY

3d•Remote

About The Position

24-MAG LLC is recruiting a full-time, fully remote AI/ML Engineer to build and enhance advanced AI-powered internal platforms, including an AI recruiting agent. The role combines applied AI engineering with Python backend development, retrieval-augmented generation (RAG), agent orchestration, cloud deployment, and continuous model evaluation. The engineer will develop production-ready AI capabilities, experiment with modern language models and agent frameworks, and improve the accuracy, reliability, and practical effectiveness of recruiting workflows. The role includes integrating LLM APIs and AI services into internal applications, building backend services and APIs, and connecting models with application services and data sources. It also involves designing prompts and multi-step agent workflows, developing RAG capabilities, implementing tool-calling patterns, and evaluating model and workflow performance. The engineer will deploy and improve AI services in cloud environments, collaborate with product and engineering teams, and maintain technical documentation and implementation quality. Core technologies and areas of focus include Python, LLM APIs, FastAPI or similar frameworks, LangChain, LangGraph, LlamaIndex or comparable tools, RAG, prompt engineering, tool calling, agent orchestration, and cloud platforms such as AWS, Google Cloud, or Azure. Compensation is $220,000–$300,000 per year. One opening is available.

Requirements

Strong professional experience in Python software engineering and backend application development.
Demonstrated experience building applications using large language models and AI APIs.
Practical knowledge of LLM integration, prompting, and AI application architecture.
Experience designing or implementing agent-based AI workflows.
Familiarity with LangChain, LangGraph, LlamaIndex, or comparable agent development frameworks.
Experience building backend APIs using FastAPI or similar Python frameworks.
Strong understanding of API design, service integration, and backend software engineering principles.
Practical experience with at least one major cloud platform, such as AWS, Google Cloud, or Azure.
Understanding of scalable application architecture and production deployment practices.
Familiarity with RAG systems and relevant retrieval workflows.
Strong analytical reasoning and software debugging capabilities.
Ability to experiment with different AI models and systematically evaluate results.
Experience assessing model performance, reliability, and output quality.
Strong understanding of prompt engineering and iterative AI application development.
Ability to collaborate effectively with engineering and product teams.
Excellent written and verbal communication skills.
Strong independent problem-solving skills and an experimental approach to technical challenges.
Strong attention to detail and commitment to software reliability and maintainability.
Ability to manage technical priorities and deliver high-quality features in a remote environment.

Nice To Haves

Experience implementing tool calling, agent orchestration, or multi-step LLM applications.
Experience delivering production-ready AI applications or AI agents.
Familiarity with model evaluation methodologies and practical AI quality assurance.
Contributions to open-source AI projects or independently developed AI applications.
Experience working in fast-paced, AI-focused technology environments.

Responsibilities

Design, develop, and enhance AI agent capabilities using modern large language models.
Build intelligent workflows supporting recruiting-related tasks and automated decision-support processes.
Integrate LLM APIs and related AI services into internal applications.
Experiment with model configurations and implementation approaches to improve agent performance.
Develop production-oriented AI features that improve platform functionality.
Build and maintain backend services using Python and modern application development frameworks.
Design and implement APIs for AI-powered platform capabilities.
Develop backend integrations connecting models, application services, and relevant data sources.
Apply software engineering best practices to maintain reliability, scalability, and code quality.
Collaborate with engineering teams to deliver maintainable backend infrastructure and product features.
Design and refine prompts, model workflows, and multi-step AI agent interactions.
Develop RAG capabilities for relevant knowledge retrieval and contextual reasoning.
Implement tool-calling and orchestration patterns for agent-based applications.
Evaluate and improve agent workflows using frameworks such as LangChain, LangGraph, or LlamaIndex.
Improve model context handling, task execution, and workflow reliability.
Evaluate the quality, accuracy, and reliability of AI-generated outputs.
Design experiments comparing model behaviour, prompting strategies, and agent implementations.
Identify weaknesses in AI system performance and implement targeted improvements.
Refine evaluation methods and quality metrics for consistent performance assessment.
Apply experimental findings to improve deployed AI features.
Deploy, maintain, and improve AI-powered services in cloud environments.
Support scalable production operations using AWS, Google Cloud, Azure, or comparable infrastructure.
Collaborate with product and engineering teams to translate requirements into practical AI solutions.
Monitor developments in LLMs, agent frameworks, and applied AI engineering tools.
Maintain technical documentation, implementation quality, and cross-functional communication.