Senior AI Research Engineer

We’re on a mission to make sure everyone has access to the law.

Backed by top VC funds and a recent $40M Series A—one of Europe's five largest Series A raises of 2024—Lawhive is poised for rapid growth and expansion into the US market.

As a pioneering legal tech platform, we're seeking a Senior Research Engineer to join our mission of democratising access to the law. This role offers the opportunity to work on cutting-edge AI products, build best-in-class user experiences, and help solve one of society's most pressing problems.

We’re looking for a Research Engineer to experiment with, develop, and refine LLM-based AI assistants, document automation systems, and case workflow optimisations. This is an opportunity to bridge cutting-edge AI research and real-world applications.

• Conduct applied research on LLM-based reasoning, multi-agent systems and developing frontier bespoke models for automating legal workflows.
• Develop prototypes and experimental models to explore novel AI-driven legal solutions.
• Design and implement retrieval-augmented generation (RAG) pipelines, leveraging embeddings, vector databases, and structured retrieval techniques.
• Optimise LLM inference and fine-tuning using techniques such as LoRA, PEFT, prompt engineering, and caching.
• Integrate multi-modal and external knowledge sources to enhance AI-driven insights.
• Research and implement autonomous agentic AI systems for complex, multi-step legal workflows.
• Stay up to date with the latest advancements in model architectures, alignment and interpretability, and orchestrating complex multi-agent systems.
• Collaborate with engineers to transition experimental models into production-ready systems.

Requirements

• Strong background in AI research, applied machine learning, and NLP.
• Experience with LLM model adaptation, fine-tuning, and inference optimization.
• Proficiency in Python, Pydantic, FastAPI, and working with LLM APIs (OpenAI, Anthropic, Mistral, etc.).
• Understanding of retrieval-augmented generation (RAG), vector databases, embeddings, and structured AI retrieval.
• Hands-on experience with LLM-based planning, reasoning, and autonomous task execution.
• Familiarity with self-supervised learning, reinforcement learning, or adaptive AI techniques.
• Ability to translate academic AI research into practical experiments and working prototypes.
• Experience deploying AI models in cloud environments such as AWS/GCP.
• MSc or PhD in AI, ML, Computer Science, or a related field.

Benefits

✈️  34 Holidays (25 days annual leave + your birthday off + bank hols in England)

  Equity (Share Options)

  Pension

⛳️  Regular team building activities, socials, and annual retreat!

20% off legal fees through Lawhive