Quick summary: We’re looking for a curious and detail-driven Prompt Engineer who loves working with Large Language Models and improving how they perform in real-world products. You’ll work directly with sintra.ai system to design, test, and optimize prompts, explore new LLM capabilities, and help elevate the quality of our platform’s AI output.
Why join Sintra?
We build AI employees for small businesses. Real helpers with personalities, not faceless chatbots. They handle the work that keeps owners up at night - answering customer emails, posting on social media, analyzing sales data. For business owners who've always worked alone, we're giving them their first team.
50,000+ businesses use Sintra because for the first time someone made AI actually useful for them. While Silicon Valley builds for tech companies, we're building for the florist who needs help with Instagram, the contractor drowning in invoices, the restaurant owner who can't keep up with reviews.
This is a unique moment in history. AI just became good enough to fundamentally change how small businesses operate. Behind every business is someone trying hard for their family. Someone with one goal - put food on the table. And our job is to help them succeed.
Having just raised our $17M seed round, we're off to the races. Small, fast-moving team building together in person. We ship daily, take ownership of what we build, and live by one principle - work is play.
What you'll do:
- Design, test, and optimize prompts for various use cases across the Sintra platform
- Run LLM evals to compare model behavior, track improvements, and identify regressions
- Build and maintain eval datasets to support consistent, measurable prompt quality
- Research LLM capabilities, best practices, and emerging techniques to improve model performance
- Run structured experiments, analyze results, and iterate on prompt strategies
- Collaborate with product, engineering, and data teams to implement prompt improvements
- Document prompt workflows, evaluation results, and experimental findings
- Identify edge cases, inconsistencies, and opportunities for improving AI responses
- Ensure prompts align with user experience, accuracy, and safety standards
Who we're looking for:
- Extensive experience working with Large Language Models (prompt engineering, fine-tuning, workflow testing, or similar)
- Strong analytical and problem-solving skills with attention to detail
- Technical aptitude - comfortable working with structured tools, APIs, or testing environments
- Ability to run systematic experiments, LLM evals, and interpret model behavior
- Experience or interest in building evaluation datasets
- Excellent written communication skills (English)
- Creative mindset for designing effective prompts and testing new approaches
- Self-driven, curious, and able to work autonomously in a fast-paced environment
What we offer
- Compensation & Equity
Top-of-market salary in Vilnius plus meaningful equity, so that you own a part of what you build.
Salary range for this role: €3,500-5,000 EUR gross / month depending on expertise and experience. - Health & Wellness
Health insurance, gym membership with personal trainer option, team lunch at the office.