Remote LLM Specialist — Prompt Engineering & AI Impact

BairesDev; United States; Remote; USD 130,000 - 190,000; Full time

Benefits offered by this job

Remote work

Competitive salary (USD)

Home office setup

Flexible hours

Paid parental leave

Vacations & holidays

Mentorship & career growth

Global team

Job summary

BairesDev is seeking an LLM Specialist to design, refine, and evaluate prompts ensuring high-quality model outputs. You’ll bridge business requirements with AI interactions and optimize performance in domain-specific contexts.

You will design prompt strategies, build evaluation methods, and collaborate with legal/compliance to meet standards. This is a 100% remote role offering competitive compensation in USD or local currency.

Qualifications

• 4+ years of experience in Prompt Engineering, AI Development, or Natural Language Processing.
• Proven expertise in designing complex prompts and implementing structured output patterns.
• Strong background in building evaluation methodologies and benchmarking model performance.
• Hands-on experience with intent classification patterns and iterative prompt refinement.
• Proficiency in Python for developing test suites and evaluating AI interactions.
• Advanced proficiency in English.

Responsibilities

• Design and implement advanced prompt engineering strategies to guide model behavior and accuracy.
• Develop structured output designs and intent classification patterns to ensure consistent AI responses.
• Create and manage rigorous evaluation methodologies to measure and iterate on model performance and reliability.
• Collaborate with legal and compliance teams to ensure LLM outputs meet strict domain‑specific standards.
• Utilize Python and testing frameworks to automate the validation and iteration of prompt effectiveness.

Skills

Prompt engineering

NLP / AI development

Python

English proficiency

Intent classification

Evaluation methodologies

Structured output design

Tools

Testing frameworks

Job description

BairesDev is seeking an LLM Specialist to design, refine, and evaluate prompts ensuring high-quality model outputs. You’ll bridge business requirements with AI interactions and optimize performance in domain-specific contexts.

You will design prompt strategies, build evaluation methods, and collaborate with legal/compliance to meet standards. This is a 100% remote role offering competitive compensation in USD or local currency.