Senior ML Engineer (LLM, Agentic AI)

Who Is Nisos?

Nisos is the human risk management company specializing in unmasking threats before they escalate. We are a trusted advisor who operates as an extension of security, intelligence, legal, and human resource teams to protect their people and business. Our intelligence-led solutions help enterprises make critical decisions, manage human risk, and drive real world consequences for digital threats.

For more information, visit: https://www.nisos.com.

What Is The Opportunity?

Join an AI/ML team designing and shipping production ML systems that combine Large Language Models (LLMs), retrieval-augmented generation (RAG), and modern agent frameworks for multi-step decision making. You will help turn massive, noisy data into actionable intelligence for analysts and customers.

What Are The Responsibilities? 

• Integrate and fine-tune LLMs for natural-language understanding, reasoning, and multi-step tool orchestration.
• Build agentic workflows (e.g. using LangGraph) to coordinate complex tasks across data sources and services.
• Architect and implement AI/ML features for pattern recognition, entity extraction, and automated intelligence gathering at scale.
• Develop scalable data pipelines and streaming architectures that process billions of heterogeneous data points.
• Create and optimize vector databases and retrieval systems for semantic search and RAG.
• Deliver production-ready APIs and microservices supporting real-time analysis and model inference.
• Own model deployment and monitoring using modern ML/LLMOps practices; drive continuous improvement in accuracy, latency, and cost.
• Evaluate LLM systems with offline metrics, golden test sets, prompt A/B tests, latency & cost optimisation.
• Collaborate with analysts and product teams to translate intelligence needs into robust ML solutions.

Who You Are

• Expert proficiency in Python, with experience of at least one of deep learning frameworks, PyTorch and TensorFlow
• Hands-on with LangChain, LangGraph, AutoGen or similar agent LLM frameworks
• Deep experience with prompt engineering, foundation model API integration and LLM finetuning
• Expertise in RAG systems with vector databases (Pinecone, Weaviate) and embedding technologies
• Strong experience with LLMOps practices for observability and traceability and LLM evaluation.
• Deep understanding of distributed systems, microservices, and real-time streaming architectures
• Strong containerization and infrastructure skills (Docker, ECS, Terraform, CloudFormation)
• Experience building production AI systems with strong safety, privacy, and ethical practices
• Familiarity with computer vision and NLP techniques for OSINT
• Understanding of adversarial AI and security implications

Required Education and Experience

• Degree in Computer Science, AI/ML, or equivalent experience
• Substantive experience in building AI/ML products at scale with proven experience in LLMs, RAGs or Agentic AI solutions
• Proven experience shipping production AI systems at scale
• Track record of building systems that process and analyze large-scale unstructured data
• Experience in security, intelligence, or OSINT platforms preferred

Where will you work? 

• Hybrid office schedule: employees balance working remotely and working at our office in Belfast City Centre.
• Flexible schedule: employees generally work normal business hours. We routinely meet in the afternoon with US-based colleagues, but we rarely schedule meetings earlier than 8 am or past 6 pm local time.

What equipment will you use?

The position requires use of Macbooks and MacOS. We ensure you can work well from home by providing Macbook Pros, monitors, peripherals, and noise-canceling headphones.