Prompt Engineer / LLM Specialist

Role Summary:

We are looking for an expert in Large Language Models (LLMs) to help build advanced AI solutions tailored to real business needs. The role focuses on fine-tuning language models, prompt optimization, and deploying systems based on technologies such as Retrieval-Augmented Generation (RAG) integrated with vector databases.

Main Responsibilities:

• Craft and refine prompts for a variety of use cases: content generation, summarization, data extraction.
• Fine-tune pre-trained LLMs with custom data to boost relevance and performance.
• Develop RAG-based applications with integrated vector search capabilities.
• Ensure AI solutions align with ethical principles such as fairness, transparency, and accountability.
• Collaborate with cross-functional teams to align technical solutions with business priorities.
• Contribute to development efforts in NLP, AI, and machine learning.
• Work with Python and SQL; use GitHub and CI/CD for automation and versioning.
• Deploy solutions on cloud platforms – Azure or GCP depending on expertise.
• Communicate complex AI concepts to both technical and non-technical stakeholders.

Key Requirements:

• 5+ years of hands-on experience in NLP, AI, and ML development.
• Strong understanding of LLM architecture and model fine-tuning.
• Proven expertise in prompt engineering, RAG techniques, and vector database integration.
• Proficiency in Python and SQL.
• Experience with CI/CD and version control systems.
• Solid working knowledge of cloud platforms (Azure and/or GCP).
• Excellent communication skills and the ability to explain technical topics clearly in English.

Nice to Have:

• Experience with OpenAI or similar AI platforms.
• Familiarity with ethical AI standards and practices.
• Experience in the financial sector.

Other Details:

This position allows for a hybrid or remote work model, with a focus on long-term collaboration through engaging and challenging international projects in the financial sector.