Remote Prompt Engineer for AI Moderation & Trust

Social Discovery Group (SDG) is one of the world's largest groups of social discovery companies, uniting millions of users on dozens of products. SDG solves the problem of loneliness, isolation, and disconnection - transforming virtual intimacy into the new normal. SDG products redefine the way people interact and connect with each other. Our portfolio includes social entertainment platforms designed to connect people online across different cultures in different parts of the world. This includes globally recognized brands such as DateMyAge, Dating.com, EuroDate, Dil Mil and Cupid Media. SDG has a presence in more than 150 countries. We bring together a team of like-minded people and IT professionals specializing in the creation and development of globally impactful social discovery products. Our international team of 1000+ professionals and digital nomads works all over the world. Our teams of digital nomads work remotely from Cyprus, Malta, the USA, Armenia, Georgia, Kazakhstan, Montenegro, Poland, Latvia, Serbia, Spain, Portugal, UAE, Israel, Turkey, Thailand, Indonesia, Japan, Hong Kong, Australia and many other locations. We’re proud to be a two-time “Great Place to Work” winner (USA & Japan, 2024–2025) and a Top-5 Company for Work-From-Anywhere Jobs (FlexJobs, 2025). We are looking for a Middle Prompt Engineer to help improve the quality and reliability of our AI moderation systems. You will work with large-scale user-generated content and optimize LLM prompts used for automated moderation of photos, profiles, and conversations. . Your main tasks will be Improve and optimize LLM prompts used for AI moderation (photos, profiles, chats) Analyze model performance and identify errors (false positives / false negatives) Work with large-scale user-generated content (UGC) and edge cases Build and improve quality evaluation processes for moderation systems Run experiments (including A/B testing) to measure prompt effectiveness Collaborate with engineers, product teams, and moderation specialists Continuously iterate on prompts based on data, metrics, and user behavior Detect and prevent moderation bypass patterns (jailbreaks, prompt injections, etc.) We Expect From You Experience working with LLMs (e.g., GPT, Claude, Gemini or similar) Hands-on experience with prompt engineering and/or LLM evaluation Understanding of AI moderation / Trust & Safety / UGC systems Ability to analyze model outputs and work with quality metrics Experience with experimentation (A/B testing, hypothesis validation) Strong analytical thinking and attention to detail Ability to work with ambiguity and iterate quickly Good communication skills and ability to work cross-functionally What Do We Offer REMOTE OPPORTUNITY to work full time; Vacation 28 calendar days per year; 7 wellness days per year (time off) that can be used to deal with household issues, to lie down and recover without taking sick leave; Bonuses up to $5000 for recommending successful applicants for positions in the company; 50% payment for professional training, international conferences and meetings; Corporate discount for English lessons; Health benefits. According to the paychecks, if you are not eligible for corporate medical insurance, the company will compensate you with up to $ 1,000 gross per year per employee. This can be spent on self-purchase of health insurance or on doctor’s fees for yourself and close relatives (spouse, children); Workplace organization. The company provides all employees with an equipped workplace and all the necessary equipment (table, armchair, wifi, etc.) in our offices or co-working locations. In the other locations, the company provides reimbursement of workplace costs up to $ 1000 gross once every 3 years, according to the paychecks. This money can be spent on the rent of the co-working room, on equipping the working place at home (desk, chair, Internet, etc.) during those 3 years; Internal gamified gratitude system: receive bonuses from colleagues and exchange them for our merchandise, team building activities, massage certificates, etc. Sounds good? Join us now! #J-18808-Ljbffr Moonfire