Full-Stack Engineer, Data

Description

• Lead the technical design and architectural decisions for our core AI product.

• Take ownership of the entire LLM lifecycle, from model selection and evaluation to deployment and monitoring, ensuring a clear and scalable design.

• Develop clean, secure, and performant serverless backend services using AWS Lambda and the wider AWS ecosystem.

• Design, build, and maintain the scaffolding for invoking Large Language Models (LLMs) via services like AWS Bedrock.

• Compare and evaluate different LLMs to determine the best fit for our use cases, establishing clear metrics and evaluation frameworks.

• Implement and manage robust data processing and storage solutions to support our AI features.

• Design and deploy cloud infrastructure using modern best practices (e.g., Infrastructure as Code).

• Implement comprehensive testing, robust exception handling, and application monitoring to ensure the high availability and reliability of our AI services.

• Take charge of your local development environment and see features through to production, collaborating with the wider team to ensure seamless product integration.

• Champion and maintain high standards for code quality, scalability, and maintainability.

Requirements

• Proven experience as a Full-Stack Engineer, with a strong portfolio of backend-focused or AI-driven projects.

• Expert proficiency in TypeScript and Node.js, with a deep understanding of modern JavaScript (ES6+), asynchronous programming patterns, and building scalable backend APIs and services.

• Extensive, hands-on experience architecting and building solutions on the AWS ecosystem. This includes core serverless services (Lambda, API Gateway, S3, EventBridge), databases (RDS, DynamoDB), security (IAM), and infrastructure as code tools (AWS CDK, CloudFormation, or Terraform).

• Strong experience in database design and management, with proficiency in both relational (e.g., PostgreSQL) and NoSQL databases. You should be comfortable with schema design, query optimization, and data modeling.

• A solid understanding of Generative AI concepts and practical experience working with LLMs.

• Comfortable with the principles of LLM design, including prompt engineering and an understanding of model evaluation techniques.

• A solid understanding of the full software development lifecycle, including testing, monitoring, and deployment.

• Experience with AWS Bedrock or similar LLM platforms (plus).

• Familiarity with LLM evaluation tools like Langfuse (plus).

Benefits

• 25 days annual leave

• 24/7 EAP and a wide range of health and wellbeing supports

• Extensive list of employee perks and benefits

Copyright © ReadingWaters 2025.