AI Engineer

For our client, a provider of financial software solutions, we are looking for a
AI Engineer
to join the newly forming core team in Poland.

About You:

As an AI Engineer, you will be a key player in our mission to bring autonomous finance to

every company in the world. You will be at the forefront of developing and deploying innovative

applications that leverage the power of Large Language Models (LLMs) and foundation models. We are looking for a candidate with a deep understanding of AI Engineering with practical experience deploying GenAI solutions at scale.

You'll Get To:

• Design, build, and deploy production-grade applications that leverage foundation models to deliver unprecedented insights and efficiency to Finance & Accounting teams.
• Develop and implement robust evaluation methodologies for open-ended AI systems, including the use of "AI as a judge" to ensure our solutions meet the highest standards of accuracy and reliability.
• Master and apply a variety of model adaptation techniques, including prompt engineering, Retrieval-Augmented Generation (RAG), and fine-tuning, to tailor foundation models to specific financial use cases.
• Create and manage datasets for training and fine-tuning models, ensuring data quality and relevance.
• Build and deploy AI agents that can automate complex financial workflows and interact with various tools and systems.
• Optimize the performance of our AI applications, focusing on reducing latency and cost to deliver a seamless user experience.
• Collaborate with cross-functional teams to identify and implement the best AI-powered solutions to address the challenges faced by the office of the CFO.

Technical/Specialized Knowledge, Skills, and Abilities:

• Proven experience in developing and deploying applications using foundation models (e.g.,GPT-4, Claude 3, Llama).
• A strong understanding of the principles of AI Engineering, as distinct from traditional Machine Learning Engineering.
• Hands-on experience with prompt engineering, including techniques for few-shot and zero-shot learning, and defensive prompt design.
• Practical knowledge of Retrieval-Augmented Generation (RAG) architecture and its application in building knowledge-intensive applications.
• Experience with fine-tuning LLMs and an understanding of when to use fine-tuning versus RAG.
• Experience with building and evaluating AI agents that can perform complex, multi-step tasks.
• Familiarity with the challenges of evaluating foundation models and experience with designing and implementing evaluation pipelines.
• Experience with building and evaluating AI agents that can perform complex, multi-step tasks.
• Proficiency in Python or C# and experience with relevant libraries and frameworks (e.g., Hugging Face Transformers, LangChain, PyTorch).

We're Even More Excited If You Have:

• Knowledge of techniques for optimizing inference, including quantization and other methods to improve latency and cost.
• Expertise in multi-modal generative models (e.g., text, image, audio) and a proven ability to apply them to create innovative enterprise solutions.
• A deep understanding of dataset engineering, including data curation, augmentation, and synthesis.
• Proven experience in designing and building end-to-end Generative AI systems, from data ingestion and model orchestration to scalable deployment and continuous monitoring.
• A strong grasp of LLMOps principles and hands-on experience with tools and platforms for managing the entire lifecycle of Large Language Models in production.
• Experience with Model Composition (MCP) techniques, demonstrating an ability to solve complex problems by intelligently combining multiple specialized models or AI agents.
• Deep knowledge of Responsible AI principles and practical experience in implementing robust guardrails, safety filters, and ethical considerations into generative models to ensure fairness, transparency, and accountability.
• Familiarity with the financial domain and the challenges of applying AI in a regulated industry.