The LLM Engineer at Precision AI will focus on building and improving an internal large language model platform used across the company.

Requirements

Support the development of an internal LLM system used for research, operations, and internal tooling
Assist with prompt engineering, structured prompting, and prompt evaluation
Work with retrieval-augmented generation (RAG) pipelines using internal documents and datasets
Help fine-tune and adapt existing foundation models using supervised fine-tuning and parameter-efficient methods
Contribute to experimentation with open-source LLMs and reasoning-oriented models
Run experiments to evaluate model quality, reliability, and failure modes
Help define and track evaluation metrics for LLM outputs (accuracy, consistency, usefulness)
Read and summarize relevant research papers, blog posts, and tooling updates
Prototype ideas and iterate quickly under guidance from senior engineers
Write clean, well-documented Python code following team standards
Contribute to internal tools and scripts that support LLM workflows
Use version control (Git/GitHub) and follow basic CI/testing practices
Work with APIs and services that integrate LLM capabilities into internal systems
Work closely with senior AI engineers and cross-functional partners
Participate in code reviews and technical discussions
Contribute to internal documentation and knowledge sharing

The LLM Engineer at Precision AI will focus on building and improving an internal large language model platform used across the company.

Support the development of an internal LLM system used for research, operations, and internal tooling
Assist with prompt engineering, structured prompting, and prompt evaluation
Work with retrieval-augmented generation (RAG) pipelines using internal documents and datasets
Help fine-tune and adapt existing foundation models using supervised fine-tuning and parameter-efficient methods
Contribute to experimentation with open-source LLMs and reasoning-oriented models
Run experiments to evaluate model quality, reliability, and failure modes
Help define and track evaluation metrics for LLM outputs (accuracy, consistency, usefulness)
Read and summarize relevant research papers, blog posts, and tooling updates
Prototype ideas and iterate quickly under guidance from senior engineers
Write clean, well-documented Python code following team standards
Contribute to internal tools and scripts that support LLM workflows
Use version control (Git/GitHub) and follow basic CI/testing practices
Work with APIs and services that integrate LLM capabilities into internal systems
Work closely with senior AI engineers and cross-functional partners
Participate in code reviews and technical discussions
Contribute to internal documentation and knowledge sharing

LLM Engineer