Senior AI Research Engineer

Clio is the global leader in legal AI technology, empowering legal professionals and law firms of every size to work smarter, faster, and more securely. Clio signed a definitive agreement to acquire vLex in 2025. This transaction is a major milestone in Clio’s platform evolution and a turning point for the future of legal work. It combines Clio’s legal operating system – trusted by more than 200,000 legal professionals – with vLex’s cutting‑edge legal intelligence platform, which includes Vincent AI, built on the industry’s most comprehensive global legal database. Together, these platforms establish a new category of intelligent legal technology at the intersection of the business and practice of law, empowering legal professionals to seamlessly manage, research, and execute legal work within a unified system.

This role is available to candidates local to our London hub, with the expectation of being in office minimum twice per week on our Anchor Days.

As a Senior AI Research Engineer, you will play a key role in developing and advancing Vincent, vLex’s groundbreaking AI, by contributing to applied research experiments that integrate cutting‑edge AI – particularly large language models (LLMs) – into real‑world legal workflows. You will work closely with software engineers and domain experts on sophisticated technical challenges to deliver innovative solutions that push the boundaries of legal technology.

What you’ll work on:

• Foundations of retrieval at scale: Re‑think how we search over vast, heterogeneous legal corpora. Exploring new approaches to chunking, query augmentation, hybrid sparse/dense embeddings, contextual embeddings, quantisation, to push the boundaries of recall, speed, and efficiency.
• Learning to rank with legal signals: Experiment with re‑ranking strategies for search results that incorporate legal‑specific signals that go beyond keyword matches and semantic similarities, to surface the most authoritative and relevant results first.
• Agentic infrastructure for legal workflows: Develop the foundations of agents that can decompose complex legal tasks, plan across multiple tools, and execute with traceability and guardrails. These are building blocks that underpin future end‑to‑end automated workflows.
• Evaluation frameworks for retrieval and agents: Design and run experiments that help us measure system performance against the needs of legal professionals: offline testbeds, human‑in‑the‑loop evaluations, implicit feedback pipelines, and alignment between lab metrics and customer satisfaction.
• Grounding and validation of model responses: Create mechanisms that ensure model responses are trustworthy by anchoring them in trusted legal sources, with clear traceability to supporting evidence, and methods for validating cited content and surfacing uncertainty when the model lacks sufficient grounding.

A day in the life might look like:

• Leading complex research projects focused on LLMs, advanced information retrieval, and novel AI applications in the legal domain, working independently with minimal supervision.
• Designing and implementing sophisticated prototypes that demonstrate the feasibility and business value of cutting‑edge research ideas, ensuring they meet production‑quality standards.
• Driving the transition of research innovations from prototype to production, collaborating closely with product and engineering teams to ensure successful integration and scalability.
• Contributing to strategic research planning by identifying high‑impact research opportunities and helping prioritise initiatives based on business value and technical feasibility.
• Staying at the forefront of AI research, particularly in NLP, LLMs, and legal AI, actively incorporating state‑of‑the‑art techniques into your work and sharing insights with the team.
• Lead technical discussions and code reviews, ensuring high standards of research quality and implementation across the team.
• Collaborating with cross‑functional stakeholders including product managers, legal engineers, and business leaders to align research efforts with strategic objectives.
• Documenting and communicating research findings through internal presentations, technical documentation, and potentially external publications or conference presentations.
• Contributing to the development of research infrastructure and best practices that enhance the team's overall efficiency and impact.

What you may have:

• Masters degree or PhD in Computer Science, Machine Learning, Data Science, Artificial Intelligence, or a related field.
• Industry experience in applied AI research or engineering.
• At least one of the following experiences:

• Information retrieval systems.
• LLM fine‑tuning and evaluation.
• LLM hosting and inference optimization.
• LLM workflow automation using prompt engineering, prompt chaining techniques, and agent orchestration frameworks.

What you will find here:

• Compensation is one of the main components of Clio’s Total Rewards Program. We have developed a series of programs and processes to ensure we are creating fair and competitive pay practices that form the foundation of our human and high‑performing culture.
• Some highlights of our Total Rewards program include:

• Competitive, equitable salary with top‑tier health benefits and dental coverage.
• Hybrid work environment, with expectation for local Clions (Vancouver, Calgary, Toronto, Dublin and Sydney) to be in office min. twice per week.
• Flexible time off policy.
• Pension contribution.
• Clioversary recognition program with special acknowledgement at 3, 5, 7, and 10 years.