Remote Prompt Engineer: Master AI Prompting & Production

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

Benefits offered by this job

Competitive salary

Equity participation

Fully remote work with flexible hours

Health, dental, and vision insurance (

Unlimited PTO with minimum 4 weeks

Learning and development budget

Conference attendance budget

MacBook Pro and peripherals

401(k) with company match

Parental leave

Home office setup stipend

Job summary

Syntas is seeking a Prompt Engineer to optimize prompts for production LLM systems across client use cases. You will design prompting strategies, build evaluation frameworks, and implement systematic prompt optimization workflows, with a focus on edge cases, failure modes, and verifiable outputs.

You will develop tooling for versioning, experiment tracking, and production monitoring, and collaborate with engineers to embed prompting best practices into applications.

Qualifications

• 3+ years with LLMs, 1 year in prompt engineering.
• Deep understanding of few-shot, chain-of-thought, self-consistency.
• Experience evaluating prompts via human or automated metrics.
• Proficiency in Python for evaluation frameworks & automation.

Responsibilities

• Design prompting strategies for diverse client use cases.
• Build evaluation frameworks for prompt performance.
• Implement systematic prompt optimization with AB testing & ablations.
• Create few-shot libraries and retrieval strategies.
• Develop structured output prompts (JSON, function calling).
• Design multi-step prompting and chain-of-thought techniques.
• Versioning, experiment tracking, and production deployment workflows.
• Build LLM-as-judge evaluation systems for scalable quality.

Skills

LLM experience

Prompting techniques

Experiment design

Python proficiency

LLM observability

Remote work discipline

Analytical reasoning

Written communication

Tools

Langfuse

LangSmith

Weights & Biases

LangChain

Job description

Syntas is seeking a Prompt Engineer to optimize prompts for production LLM systems across client use cases. You will design prompting strategies, build evaluation frameworks, and implement systematic prompt optimization workflows, with a focus on edge cases, failure modes, and verifiable outputs.

You will develop tooling for versioning, experiment tracking, and production monitoring, and collaborate with engineers to embed prompting best practices into applications.