Senior Applied AI Engineer (LLMs, Azure)

We are seeking a Senior Applied AI Engineer to join our AI platform team, focusing on leveraging large language models (LLMs) and Azure technologies for advanced document understanding and data extraction. You will collaborate with cross-functional experts to design, optimize and validate prompt strategies, ensuring high-quality, secure and scalable AI solutions. ResponsibilitiesDesign and optimize advanced prompts for document understanding and data extraction use casesCollaborate with business stakeholders to understand document structures, semantics and key-value relationshipsCreate PoCs using Python to validate prompt effectiveness and iterate quicklyMaintain a prompt library with a focus on quality, reusability and compliance with security and privacy guidelinesPerform prompt validation, stress testing and failover scenario modeling for different LLMsAnalyze LLM output quality, fine-tune prompts and propose model-specific prompt strategiesWork with ML engineers on fine-tuning initiatives to improve model accuracy for specific document domainsDocument best practices, prompt strategies and experiment results in a structured formatIdentify and mitigate risks related to prompt injection, hallucination or other LLM-specific vulnerabilities RequirementsProven experience with at least 2 LLM production projects designing and deploying prompts in real-world applicationsExcellent understanding of prompt structure and contextsProficiency in Python with experience in LLM APIs, prompt engineering frameworks and data manipulation tools such as PandasExperience with at least one fine-tuning or retrieval-augmented generation (RAG) pipeline implementationFamiliarity with prompt evaluation tools and metrics such as BLEU, ROUGE and semantic similarity, as well as human-in-the-loop validationUnderstanding of LLM-related security concerns including prompt injection, output filtering, API limitations and output structuringExcellent communication skills and ability to translate complex document requirements into actionable prompt logicStrong analytical mindset with attention to both high-level design and low-level output consistency Nice to haveExperience with vector databases and retrieval-augmented generationExposure to tools like LangChain, LlamaIndex or similarPrior work with OCR, NLP or intelligent document processing (IDP) pipelines We offerWe gather like-minded people:Engineering community of industry professionalsFriendly team and enjoyable working environmentFlexible schedule and opportunity to work remotely within PolandChance to work abroad for up to 60 days annuallyBusiness-driven relocation opportunitiesWe provide growth opportunities:Outstanding career roadmapLeadership development, career advising, soft skills, and well-being programsCertification (GCP, Azure, AWS)Unlimited access to LinkedIn Learning, Get Abstract, Cloud GuruEnglish classesWe cover it all:Stable income (Employment Contract or B2B)Participation in the Employee Stock Purchase PlanBenefits package (health insurance, multisport, shopping vouchers)Strategically located offices featuring entertainment and relaxation zones, table tennis and football, free snacks, fantastic coffee, and moreReferral bonusesCorporate, social and well-being eventsPlease, note:The set of bonuses might vary based on the role you apply for – specifics will be discussed with our recruiter during the general interview.We will reach out to selected candidates exclusively. EPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.