Senior Software Engineer, Infrastructure

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

Lawhive is an online platform for consumers and small businesses to get legal help for a fraction of the cost of a law firm. Our platform combines regulated human lawyers collaborating alongside the world’s first AI lawyer specifically built for consumer legal work.

Equal access to the law is one of the biggest and most pressing unsolved problems in society today. We’re passionate about leveling the playing field and believe access to the law should be a basic utility in society.

Our AI lawyer Lawrence is built on top of our own fine-tuned LLM who has passed the Solicitors Qualifying Exams (SQE).

We have backing from leading US and UK VC funds including Google Ventures, Balderton Capital and TQ Ventures (who have funded 82 unicorns between them!). We recently secured a $40m Series A funding round to facilitate international expansion and to grow our team. This represents one of the five largest Series A rounds in Europe for 2024!

The Role

Responsibilities

• Build & Improve Backend Systems: Work with Python (FastAPI, Pydantic) to develop robust APIs and services that interface with LLMs.
• Develop & Maintain Scalable Infrastructure: Design, implement, and optimise cloud-based infrastructure for our AI and legal automation platform.
• Optimise AI Workloads: Architect and scale compute infrastructure to support AI inference, batch processing, and real-time interactions.
• Manage Event-Driven Architecture: Build and maintain event-driven systems for scalable, real-time processing.
• Long-Running Workflows & Orchestration: Evaluate and implement workflow orchestration solutions to handle complex AI pipelines and legal automation.
• Real-Time Communication Infrastructure: Optimise communication methods to improve chatbot responsiveness and user experience.
• Document Storage & Retrieval: Work on indexing and retrieval mechanisms using OpenSearch, S3, and AI-assisted document processing.
• Build Data Pipelines: Design and implement efficient ETL pipelines to ingest, transform, and store data from multiple sources (APIs, websites, legal knowledge bases).
• Infrastructure Decision-Making: Influence and drive architectural decisions to ensure scalability, reliability, and cost-effectiveness.
• Researcher Enablement: Provide tools and infrastructure to support AI and data research teams (e.g., Langfuse, experiment tracking, dataset management).

Our Engineering Culture

• Ship daily - We’re building and releasing features fast, going from idea to production in hours rather than weeks.
• Empathise with users - Lawyers and legal clients have unique perspectives, preferences and expectations. We build products which understand them deeply.
• Strive for excellence - We’re ambitious and moving fast. The whole business is pushing to be a category defining legal tech company.
• Constantly learning and experimenting - We’re at the cutting edge of using AI to directly improve people’s lives. We take a blue-sky but pragmatic approach to how we apply new technologies.

Our Tech Stack

• TypeScript (Full-stack)
• React + Next.js, Tailwind, Prisma, tRPC
• PostgreSQL, MongoDB, Redis
• Serverless, AWS, Google Cloud, Github Actions
• DBT, BigQuery
• Terraform
• Python

• Strong Backend Development Skills: Proficiency in Python, FastAPI, Pydantic.
• Infrastructure Expertise: Experience with AWS services (Lambda, S3, ECS, EventBridge, RDS, OpenSearch) and Terraform.
• Event-Driven Systems Knowledge: Experience designing and implementing event-driven architectures (SNS/SQS, Kafka, Redis Streams, etc.).
• Orchestration & Workflows: Experience with long-running workflow solutions like Ingest, Step Functions, Temporal, or Airflow.
• Real-Time Systems: Understanding of real-time communication protocols such as WebSockets and SSE.
• Data Engineering Mindset: Experience designing scalable ETL pipelines and working with structured/unstructured data.
• Security & Reliability Focus: Familiarity with best practices for cloud security, IAM, and infrastructure reliability.
• Strong Debugging & Problem-Solving Skills: Ability to investigate and solve production issues in distributed systems.

Nice to Have

• Scaling AI Workloads: Familiarity with optimising and running AI/ML workloads in production (batch vs. real-time inference, GPU utilisation, etc.).
• Knowledge of Vector Databases: Experience with vector databases.
• Hands-On Experience with Kubernetes: Proficiency in managing Kubernetes clusters and deploying applications.
• Experience with agentic AI or autonomous AI systems.
• Prior Experience in Legal Tech: Understanding of the legal industry and experience working with legal technology solutions.