Website:
Job details:
About Us
We are building a next-generation technical assessment platform designed for the AI era. Instead of testing developers on traditional algorithmic puzzles, we evaluate how engineers actually work today: prompting LLMs efficiently and debugging complex, AI-generated code.
We currently have a fully operational code execution sandbox and live debugger running on AWS. We are now expanding our core team to bring our AI-driven testing environments to production.
The Role We are looking for a rigorous Backend Engineer to integrate LLMs into our core infrastructure. You will be responsible for building robust, resilient backend systems capable of deterministically evaluating non-deterministic AI outputs.
What you will build:
- Prompt Evaluation Engines: Architecting systems that score users on prompt efficiency, token usage, and solution optimization.
- Dynamic Flaw Generation: Building pipelines that interact with LLMs to generate realistically flawed legacy code for candidates to debug.
- Secure API Integration: Connecting LLM APIs (Amazon Bedrock/OpenAI) to our secure AWS ECS sandboxes using strict parsers and structured data formats.
What you need:
- Strong backend engineering fundamentals (API design, database architecture, clean code).
- Real-world experience integrating LLMs into production applications (understanding context windows, rate limits, and system prompting).
- Familiarity with AWS infrastructure, specifically containerized environments (Docker/ECS) and databases (RDS, ElastiCache).
Click on Apply to know more.