JOB DESCRIPTION

At the forefront of the rapidly evolving artificial intelligence landscape, our organization is seeking a talented LLM Agent Specialist to join our innovative team. In 2025, as autonomous AI agents and large language models continue to transform business operations, this role represents a critical intersection between cutting-edge AI technologies and practical business applications. You will serve as the vital connector between our front-end team and core infrastructure developers, leveraging the latest advancements in multi-agent systems, retrieval-augmented generation (RAG), and AI AGENT methodologies to drive our technological capabilities forward.

REQUIREMENTS:

• Advanced proficiency in AI AGENT models with demonstrated experience using modern AI and ML libraries, particularly those focused on LLM implementation such as LangChain, LlamaIndex, and Hugging Face Transformers.
• Experience developing and deploying AI agents to perform reasoning, planning, and autonomous task execution. Knowledge of multi-agent coordination systems is highly desirable.
• Strong understanding of prompt engineering methodologies, including best practices for structuring prompts, handling context limitations, and optimizing for specific outputs.
• Practical experience with Retrieval-Augmented Generation (RAG) systems, including document processing, vector databases, and context-aware retrieval mechanisms.
• Knowledge of LLM fine-tuning techniques, including parameter-efficient methods such as QLoras and Loras to customize models for specific domains or tasks.
• Familiarity with knowledge graphs and semantic databases, and experience interfacing these systems with LLMs to improve information retrieval and contextual understanding.
• Experience with data preprocessing techniques to improve model training and inference performance, including handling structured and unstructured data sources.
• Proficiency with modern AI deployment infrastructures, including containerization technologies like Docker, and familiarity with cloud platforms such as AWS, Google Cloud, or Azure.
• Strong problem-solving skills and the ability to translate complex business requirements into effective AI agent implementations.
• Excellent communication skills with the ability to explain complex AI concepts to non-technical stakeholders and collaborate effectively across departments.Demonstrated passion for keeping up with the latest developments in AI technology, with evidence of self-directed learning and experimentation.

PORTFOLIO REQUIREMENTS:

• Please include a link to your GitHub profile or portfolio showcasing relevant LLM agent projects and prompt engineering work. Projects demonstrating multi-agent systems, RAG implementations, or creative prompt engineering solutions are particularly valuable.
• Examples of AI agents you’ve developed that solve specific business problems or automate complex workflows will strengthen your application.
• Contributions to open-source AI projects or research papers are a plus but not required for junior candidates.

DESIRED EDUCATION

Diploma

ROLE OVERVIEW

As AI agents have become increasingly sophisticated in their reasoning capabilities and multi-modal interactions, we need a specialist who can harness these powerful tools to optimize our operational infrastructure and integrate seamlessly with our existing technology stack. This position offers the opportunity to work with state-of-the-art LLM technologies while developing practical, business-focused applications that drive measurable results.

KEY RESPONSIBILITIES

The successful candidate will be instrumental in developing and deploying our next generation of AI solutions, specifically focusing on:

• Designing and implementing autonomous AI agent systems that leverage the latest advancements in reasoning, planning, and multi-agent coordination to optimize our operational infrastructure. This includes developing specialized agents for different business functions and ensuring they work together coherently.
• Exploring and implementing cutting-edge technologies related to LLM agent engineering platforms (AgentOps), including RAG systems, reasoning frameworks, planning algorithms, specialized toolkits, and multi-agent coordination protocols to enhance our technological capabilities.
• Developing and fine-tuning prompts for large language models to ensure consistent, accurate, and contextually appropriate outputs across different business applications and use cases. This includes creating systematic approaches to prompt optimization and version control.
• Working closely with IT infrastructure developers to construct high-performance, cost-effective LLM agent service architectures that ensure service availability while minimizing computational costs.
• Collaborating with our development team to deploy AI tools that automate design processes and enhance creative workflows through natural language and multi-modal interfaces.
• Staying current with the rapidly evolving field of AI agents and prompt engineering, continuously bringing new methodologies and best practices to our organization.
• Providing AI-related insights and guidance to cross-functional teams, translating complex technical concepts into accessible language that supports our strategic business goals.