AI/LLM Data Engineer: Prompting, Pipelines & Production

Stylitics; New York (NY); On-site; USD 120,000 - 190,000; Full time

Job summary

Stylitics is seeking a versatile AI/LLM Data Engineer to shape the future of how Stylitics leverages large language models. You will fuse data science, software engineering, and prompt design to prototype, test, and deploy LLM workflows powering automation and content generation at scale.

You'll work with cross‑functional teams, contribute to production code in Clojure and Python, build dashboards, and develop internal tooling to reuse prompts, test cases, and model evaluations.

Qualifications

• Very strong SQL experience and data visualization skills.
• Experience contributing to production code.
• Experience with LLMs testing and prompt engineering.
• Proficiency in Python for experimentation and tooling.
• Solid understanding of system design and APIs.
• Ability to work cross‑functionally with product, design, and engineering.

Responsibilities

• Prompt engineering and testing with LLMs
• Context engineering to determine the right data
• Agentic workflow design
• Monitor and test LLM performance
• Contribute to production code (Clojure + Python)
• Analyze large data sets and build dashboards
• Develop internal tooling for prompt reuse, versioning, and test cases

Skills

Prompt engineering

Context engineering

LLM testing

Python programming

Clojure

SQL

Data visualization

Education

Computer Science degree

Data Science degree

Statistics degree

Tools

Google Cloud

GitLab

ClojureScript

Git

Cloud Functions

Job description

Stylitics is seeking a versatile AI/LLM Data Engineer to shape the future of how Stylitics leverages large language models. You will fuse data science, software engineering, and prompt design to prototype, test, and deploy LLM workflows powering automation and content generation at scale.

You'll work with cross‑functional teams, contribute to production code in Clojure and Python, build dashboards, and develop internal tooling to reuse prompts, test cases, and model evaluations.