Remote AI Engineer — LLM/RAG Production Systems

Tempus Unlimited, Inc.; Pennsylvania; Remote; USD 100,000 - 140,000; Full time

Benefits offered by this job

Sign on bonus

Work/Life Balance

Paid time off - 25 days per year

14 paid Holidays

Tempus Wellness - Medical, Dental, Dep

Life insurance & disability

403(b) Retirement Plan with matching

Continuing Education, Training and Adv

Job summary

Tempus Unlimited, Inc. is seeking an AI Engineer to design, deploy, and maintain scalable LLM-powered applications and agentic pipelines. You will work with IT teams to integrate AI models into production systems using REST APIs and SDKs, while developing Retrieval-Augmented Generation features and semantic search capabilities.

The role emphasizes fine-tuning foundation models, building robust data pipelines, and ensuring monitoring and security for a modern AI platform.

Qualifications

• Design and build LLM-powered applications, APIs and agentic pipelines.
• Develop RAG systems and semantic search features.
• Fine-tune foundation models for specific use cases.
• Model development, training, evaluation and iteration on ML models using real-world datasets.
• Setup monitoring, alerting and logging for model health and drift.
• Translate business problems into AI/ML solution designs.

Responsibilities

• Design and build LLM-powered applications, APIs and agentic pipelines.
• Integrate AI models into production systems via REST APIs and SDKs.
• Develop RAG systems and semantic search features.
• Fine-tune models for specific use cases and maintain data pipelines.
• Benchmark model performance and ensure production latency requirements.

Skills

Python

SQL

ETL Pipeline

PyTorch

TensorFlow

Llama index

LangGraph

Education

Bachelor's degree in a related field

High School Degree or equivalent with relevant experience

Tools

APIs / SDKs

Job description

Tempus Unlimited, Inc. is seeking an AI Engineer to design, deploy, and maintain scalable LLM-powered applications and agentic pipelines. You will work with IT teams to integrate AI models into production systems using REST APIs and SDKs, while developing Retrieval-Augmented Generation features and semantic search capabilities.

The role emphasizes fine-tuning foundation models, building robust data pipelines, and ensuring monitoring and security for a modern AI platform.