Artificial Intelligence (AI) Engineer

• Build intelligent AI agents, LLM applications and RAG solutions
• Work with Python, LangChain, LangGraph and vector databases
• Own end-to-end AI development, from architecture to production

Location: Malta / London
Working Model: Hybrid
Industry: iGaming / Artificial Intelligence / Software Development
 
About the Opportunity
We are looking for an experienced Artificial Intelligence (AI) Engineer to join an established international technology business operating within the iGaming industry.
This is an opportunity to work on innovative AI-powered solutions, developing intelligent agents and generative AI systems that automate complex processes, improve operational efficiency and deliver measurable business value.
You will be responsible for designing, developing and deploying production-ready AI applications, combining Large Language Models (LLMs), agent orchestration frameworks, backend engineering and modern cloud technologies.
The role goes beyond prompt engineering, offering genuine ownership of end-to-end AI solutions, from initial architecture and prototyping through to production deployment and continuous optimisation.
You will collaborate closely with Product and Engineering teams to develop scalable, reliable and secure AI solutions.
 
Key Responsibilities
AI Agent Development

• Design and develop autonomous and semi-autonomous AI agents capable of reasoning, planning, tool usage and multi-step task execution.
• Build intelligent workflows using AI orchestration frameworks such as LangChain, LangGraph or similar technologies.
• Develop memory systems, retrieval pipelines and integrations with external tools and internal services.
• Design and optimise agent-based solutions that automate complex business processes.
• Continuously improve agent performance, reliability and task completion rates.

 
LLM Integration & RAG Development

• Integrate Large Language Models (LLMs) into business applications using OpenAI or comparable model APIs.
• Design and implement Retrieval-Augmented Generation (RAG) solutions using vector databases and semantic search technologies.
• Develop structured output pipelines, prompt chains and advanced LLM workflows.
• Work with vector databases such as Pinecone, Weaviate, FAISS or equivalent technologies.
• Build evaluation frameworks to measure model performance, output accuracy, hallucination rates and overall effectiveness.
• Implement appropriate guardrails, testing methodologies and quality controls.

 
Python Backend Engineering & Production Systems

• Develop robust Python-based backend services, APIs and AI integrations.
• Design scalable architectures using REST APIs, microservices and serverless technologies.
• Integrate AI solutions with internal platforms, data sources and existing business systems.
• Ensure production AI services meet requirements for reliability, performance, scalability and security.
• Implement monitoring, logging and observability to support production environments.
• Optimise system latency, infrastructure usage and AI-related operational costs.
• Troubleshoot technical issues and continuously improve deployed AI services.

 
Collaboration & AI Innovation

• Work closely with Product teams to understand business challenges and translate requirements into practical AI solutions.
• Collaborate with Engineering teams to integrate and deploy AI services into production environments.
• Ensure AI solutions align with relevant compliance, security and governance requirements.
• Research and evaluate emerging AI technologies, frameworks and development approaches.
• Prototype and test new solutions to improve automation, reasoning accuracy and system intelligence.
• Contribute to engineering best practices and the continuous improvement of AI development processes.

 
Requirements

• Strong hands-on experience developing AI agents, including tool integration, memory systems and multi-step reasoning workflows.
• Advanced programming skills in Python, with strong backend development experience.
• Experience designing and developing REST APIs, asynchronous processes, data pipelines and system integrations.
• Practical experience integrating OpenAI or similar LLM APIs into production applications.
• Strong experience implementing RAG solutions, semantic search and vector databases.
• Familiarity with technologies such as Pinecone, Weaviate, FAISS or similar platforms.
• Experience developing evaluation and testing frameworks for LLM applications, including prompt testing, benchmarking and guardrails.
• Strong understanding of software architecture and the ability to design complete AI solutions rather than isolated AI features.
• Excellent analytical and problem-solving skills, with the ability to break down complex requirements into practical technical solutions.
• Strong communication skills and the ability to explain technical concepts to both technical and non-technical stakeholders.
• A proactive approach to ownership, with a focus on delivering reliable, scalable and production-ready systems.

 
Nice to Have

• Experience with AI orchestration frameworks such as LangChain, LangGraph, LlamaIndex or Semantic Kernel.
• Familiarity with Docker, Kubernetes and containerised application deployment.
• Experience with cloud platforms such as AWS or Google Cloud Platform, including serverless environments.
• Knowledge of embeddings, ETL pipelines and structured or unstructured data processing.
• Experience with monitoring, observability, logging and distributed tracing.
• Understanding of AI governance, responsible AI development and security considerations.
• Experience mentoring engineers or contributing to technical best practices.
• Commercial awareness and an understanding of how AI automation can deliver measurable business improvements.

 
What Success Looks Like
Success in this role will be measured through:

• Reliability and task completion rates of AI agents.
• Performance, latency and availability of deployed AI services.
• Reduction in manual processes through intelligent automation.
• Speed of prototyping and delivering new AI solutions.
• Improvements in model accuracy and reduction of hallucinations.
• Efficient deployment and continuous improvement of production AI applications.

 
Why Consider This Opportunity?

• Work with modern Agentic AI, LLM and RAG technologies.
• Build AI-powered solutions with real-world applications in the iGaming industry.
• Take ownership of AI projects from architecture and development through to production.
• Collaborate with experienced Product and Engineering professionals.
• Explore emerging AI technologies and contribute to innovative development initiatives.
• Work in an international technology environment.
• Benefit from a hybrid working arrangement in Malta or London.