Backend / AI Engineer
Build the AI engine behind real-time interview assistance, from speech recognition to context-aware answers.
About the role
As a Backend / AI Engineer, you will build the systems that turn a live interview question into an instant, accurate, context-aware answer. This is the technical heart of the product, where latency, reliability, and answer quality matter most.
You will work on speech-to-text pipelines, prompt engineering, retrieval over a candidate's resume and notes, and the orchestration that ties large language models into a fast, streaming experience. You will measure what you ship and tune it relentlessly.
We are looking for someone who is comfortable in Python, curious about applied AI, and disciplined about performance. You will have a lot of room to shape how the AI layer evolves.
What you'll do
- Build and maintain real-time speech and language pipelines that power live assistance.
- Design prompts and retrieval flows that produce accurate, on-context answers.
- Integrate and orchestrate large language models with streaming responses.
- Optimize latency and cost across the AI request path.
- Build evaluation harnesses to measure and improve answer quality.
- Expose clean back-end services and edge functions for the front end to consume.
What we're looking for
- Experience with Python and building back-end services or data pipelines.
- Hands-on work with LLMs, NLP, or applied machine learning.
- A working understanding of prompt engineering and retrieval augmented generation.
- Interest in real-time audio or speech processing.
Nice to have
- Experience with streaming inference and low-latency systems.
- Familiarity with vector databases and embeddings.
- Exposure to Supabase or PostgreSQL.
Apply for Backend / AI Engineer
Fill out the form below and attach your resume (PDF, max 5MB).