AI / ML Engineer

We are looking for a goal‑oriented and driven AI/ML Engineer with strong experience in building, deploying, and scaling AI/ML applications. The ideal candidate will have hands‑on experience with generative AI, agentic AI systems, RAG applications, LLM platforms, APIs, cloud deployment, and production‑ready AI architectures.

Key Responsibilities

• Develop, train, fine‑tune, and optimise machine learning, generative AI and neural network models to meet specific business and functional requirements.
• Design and build generative AI applications, agentic AI workflows, and multi‑agent architectures using modern AI frameworks and orchestration tools.
• Build Retrieval‑Augmented Generation applications, including GraphRAG solutions using knowledge graphs, Neo4j, Astra DB, vector databases, and related retrieval technologies.
• Work with both open‑source and closed‑source large language models to build scalable AI applications, including model routing, prompt engineering, evaluation, and optimisation.
• Design and implement voice‑based AI solutions, including speech‑to‑text, text‑to‑speech, conversational AI, and voice‑enabled intelligent assistants.
• Create robust API endpoints using tools such as FastAPI to enable seamless access to AI models and integration with external systems and applications.
• Architect and develop a user‑friendly AI platform where multiple AI models can be accessed, managed, and utilised through API calls.
• Contribute to the design of scalable, reliable AI systems, including queue‑based processing, asynchronous workflows, distributed services, caching mechanisms, and production‑grade backend architecture.
• Optimise LLM performance and scalability using caching mechanisms such as KV cache, response caching, prompt caching, and efficient model‑serving strategies.
• Implement observability, logging, tracing, monitoring, and evaluation workflows using tools such as Langfuse and related platforms to track system performance, reliability, cost, and user interactions.
• Deploy AI/ML applications across different cloud providers and server environments, ensuring scalability, reliability, security and performance.
• Continuously monitor, update, and improve models, APIs, workflows, and platforms based on user feedback, system performance, and evolving AI technologies.

Skills And Qualifications

• Minimum 3 years of experience in building AI/ML software and production‑ready AI applications.
• Strong expertise in machine learning, neural networks, deep learning, and generative AI applications.
• Proficiency in Python and AI/ML frameworks such as TensorFlow, PyTorch, NumPy, LangChain, LangGraph, FastAPI and related tools.
• Experience with agentic AI, multi‑agent architecture, RAG, GraphRAG, and LLM‑based application development.
• Hands‑on experience with Langfuse, LiteLLM, observability tools, tracing, model monitoring and AI evaluation workflows.
• Experience working with queues, asynchronous processing, caching mechanisms, scalable system design and backend architecture.
• Strong understanding of knowledge graphs, vector databases, Neo4j, Astra DB and graph‑based retrieval systems.
• Experience with both open‑source and closed‑source LLMs.
• Experience deploying AI applications across different cloud providers and server environments.
• Good understanding of software engineering best practices, including clean code, testing, documentation, CI/CD, version control and maintainable system design.
• Excellent problem‑solving abilities with strong attention to detail.
• Strong communication skills and the ability to collaborate effectively in a team‑oriented environment.

Bonus / Preferred Experience

• Experience implementing voice‑based AI applications, including conversational AI, speech‑to‑text, text‑to‑speech and voice assistant technologies.
• Experience scaling LLM applications using caching mechanisms such as KV cache, prompt caching, response caching and efficient inference strategies.
• Experience working across multiple cloud providers.
• Experience integrating both open‑source and closed‑source LLMs into production applications.
• Experience with advanced LLM operations, including model routing, cost optimisation, monitoring and performance tuning.

Educational Requirements

Bachelor’s or Master’s degree in Computer Science, Engineering, Artificial Intelligence, Data Science, or a related field, with a focus on AI/ML.

Working Hours

Candidates must be available to work core UK business hours, 9:00–17:30 GMT/BST, Monday‑Friday.

#J-18808-Ljbffr…