Senior Prompt Engineer - Remote LLM Architect

Bright Vision Technologies; North Brunswick Township (NJ); Remote; USD 100,000 - 150,000; Full time

Job summary

Bright Vision Technologies is seeking a seasoned Prompt Engineer for a 100% remote position in the United States. You will define and lead strategy, patterns, and tooling for designing prompts, agentic workflows, and LLM-based architectures across the organization.

The role requires shipping LLM-powered products and applying responsible AI practices while guiding teams and improving reusable patterns. Ideal candidates bring extensive experience with LLM APIs, retrieval-augmented generation, and

Qualifications

• Bachelor’s or Master’s degree in a relevant field.
• Significant software engineering experience with LLM-based applications.
• Proven track record shipping LLM-powered products to production.
• Strong Python skills and modern framework experience.

Responsibilities

• Define organization-wide patterns and architectures for LLM-based apps.
• Design prompt structures and retrieval strategies for production use cases.
• Architect agentic systems with tool use, planning, memory, and multi-step reasoning.
• Lead retrieval-augmented generation pipelines including chunking and reranking.
• Develop evaluation frameworks for prompt quality and end-to-end task success.

Skills

Python

LLM architectures

Agent frameworks

Vector databases

Mentoring

Education

Bachelor’s or Master’s in Computer Science/Computational Linguistics

Tools

OpenAI API

Git

Docker

Jupyter

Job description

Bright Vision Technologies is seeking a seasoned Prompt Engineer for a 100% remote position in the United States. You will define and lead strategy, patterns, and tooling for designing prompts, agentic workflows, and LLM-based architectures across the organization.

The role requires shipping LLM-powered products and applying responsible AI practices while guiding teams and improving reusable patterns. Ideal candidates bring extensive experience with LLM APIs, retrieval-augmented generation, and