Lead AI Application Engineer

About the Role

We are looking for an AI Application Engineer to integrate foundational models into innovative tools and workflows for our clients, with a strong focus on building agentic tools that adapt and respond to complex user needs. You will be at the forefront of AI-powered product development, focusing on embedding foundational models into applications, fine-tuning workflows, and ensuring seamless performance. The ideal candidate has experience working in a consulting or agency environment and thrives in dynamic, project-based work.

This is a hands-on role where you will be responsible for building and implementing systems from the ground up. You would write production-level code while defining processes and best practices for future team growth.

Responsibilities

• Integrate APIs for foundational models (e.g. OpenAI, Anthropic, Hugging Face) into scalable applications.
• Develop and optimize workflows for foundational model use cases, including prompt engineering, embedding generation, and real-time decision-making for agentic tools.
• Implement and manage vector-based search systems and retrieval-augmented generation (RAG) setups.
• Build and refine tools with adaptive agentic capabilities to enable autonomous decision-making and user interactions.
• Monitor the performance of AI systems, troubleshoot issues, and improve outputs to align with client needs.
• Collaborate with data engineers to integrate harmonized data into AI workflows.
• Work with full-stack engineers to embed AI functionalities into user-facing applications.
• Stay updated on the latest advancements in AI APIs, tools, and techniques to deliver innovative solutions.
  

Requirements

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or a related field.
• A minimum of 6 years of professional experience in AI application development or software engineering.
• Proven experience working in a consulting or agency environment on project-based work.
• Advanced proficiency in Python and frameworks like LangChain for building AI-powered applications.
• Strong knowledge of foundational model APIs and embedding techniques.
• Hands-on experience with vector databases (e.g. Pinecone, Weaviate) and RAG workflows.
• Familiarity with deploying AI applications in cloud environments (AWS, Azure, or GCP).
• Ability to translate complex client needs into technical solutions using foundational models.
• Experience building tools with agentic capabilities to adapt and automate workflows.
• Advanced English skills, both written and verbal, with the ability to communicate effectively in an international team.
  

Preferred Qualifications

• Experience with MLOps practices for managing AI systems in production.
• Knowledge of schema design and structured data preparation for AI workflows.
• Understanding of model performance evaluation and optimization.