Inference Engineer

Job Summary

A company is looking for a Member of Engineering (Inference).

Key Responsibilities

• Follow the latest research on LLMs, inference, and source code generation
• Propose and evaluate innovations in the quality and efficiency of inference
• Monitor and implement LLM inference metrics in production

Required Qualifications, Training, and Education

• Experience with Large Language Models (LLM) and computational properties of transformers
• Knowledge of distributed and lower precision inference
• Strong engineering background with theoretical computer science knowledge
• Programming experience in Python, C/C++, CUDA, and related technologies
• Research experience in applied deep learning or related fields is a plus