Назад
Company hidden
2 дня назад

AI Applied Engineer (LLM)

180 - 220PLN
Формат работы
hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Poland
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
AI Applied Engineer (LLM) (AI/SaaS): Developing an AI-powered SaaS platform that automates the KYB process, with an accent on prompt engineering, LLM experimentation, model evaluation, and document data extraction. Focus on designing measurable experiments, analyzing errors, validating structured outputs, and optimizing accuracy, latency, throughput, and AI unit economics.

Location: Hybrid in Gdańsk, Poland, with regular in-studio collaboration in Gdańsk Wrzeszcz

Salary: 180–220 PLN/hour + VAT on B2B, or 22,100–27,000 PLN gross on UoP

Company

hirify.global partners with ambitious brands to create digital products across strategy, UX, engineering, and long-term growth.

What you will do

  • Develop AI solutions for an AI-powered SaaS platform automating every stage of the KYB process.
  • Experiment with off-the-shelf Large Language Models and select suitable models and methods.
  • Design, optimize, and test prompts, including structured outputs and hallucination mitigation.
  • Build ground-truth datasets, select task-appropriate metrics, benchmark approaches, and perform deep-dive error analysis.
  • Improve document processing and data extraction from PDFs, scans, web pages, and complex multilingual documents.
  • Optimize trade-offs between model quality, latency, throughput, and AI unit economics.

Requirements

  • At least 7 years of experience in software engineering, machine learning engineering, or a similar field, including at least 2 years developing and maintaining LLM-based solutions in production.
  • Strong proficiency in Python and practical experience integrating and using LLM APIs programmatically for real-world business problems.
  • Hands-on LLM evaluation experience, including ground-truth datasets, precision, recall, field-level accuracy, error analysis, and data-backed validation of improvements.
  • Experience designing, testing, and optimizing prompts, working with structured outputs, and mitigating hallucinations.
  • Research-driven experience setting baselines, formulating hypotheses, designing structured experiments, and benchmarking models against measurable outcomes.
  • Experience extracting and classifying data from unstructured sources such as PDFs, scans, web pages, and complex multilingual documents.
  • Solid understanding of model uncertainty, output validation, and data traceability, including linking extracted information to its exact document source.
  • Awareness of AI unit economics, latency, and throughput, with the ability to make informed model choices and optimize trade-offs.
  • Ability to work independently at a senior level with full ownership from problem identification and experimentation through implementation and final evaluation.
  • Strong written and spoken Polish and English.

Nice to have

  • Experience working with multimodal or vision LLMs.

Culture & Benefits

  • Ownership and influence over the products being built, with a focus on business value over technical perfection.
  • Continuous feedback, open communication, regular 1:1s, mentoring, workshops, and knowledge sharing.
  • Flexible working hours with a start time between 7:00 and 10:00.
  • Hybrid collaboration, high-quality equipment including a MacBook and testing devices, and an individual training budget.
  • English classes in small groups, private medical care through Compensa, MultiSport, and team gatherings.

Будьте осторожны

Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →