Senior AI Engineer, Code Generation - Caffeine.ai

We are seeking a highly skilled Senior AI Engineer, Code Generation to join our team, focusing on LLM-based code generation for Caffeine, our platform that lets technical and non-technical users create and update sophisticated online apps just by chatting with AI. The role involves post-training and optimizing large language models (LLMs), multi-agent architectures, and retrieval-augmented generation (RAG). The candidate will play a crucial role in enhancing the core of Caffeine through innovative AI solutions, high-quality software implementation, systematic evaluations and benchmarking, and impactful optimizations. You will collaborate closely with other AI engineers, software engineers, and domain experts to push the frontier of LLM for code generation in Caffeine.

Key Responsibilities:

• Develop and apply sophisticated multi-agent architectures and prompt engineering to optimize our AI solutions.
• Optimize LLM post-training pipelines (Supervised finetuning, Reinforcement Learning)s 
• Implement scalable context engineering pipelines (incl. RAG) to improve retrieval quality and reasoning.
• Establish systematic evaluation and benchmarking frameworks to assess LLM performance.
• Lead experiments and apply the latest research directions in LLMs, ensuring impactful implementation.
• Implement high-quality AI components, tools, and integrations, practicing clean coding and professional software engineering methods.
• Collaborate cross-functionally with engineers, product managers, and data scientists, to align solutions with business and technical goals.

Required Qualifications:

• Master’s or PhD degree in Computer Science, Data Science, or a closely related field.
• 2+ years of professional AI experience with large language models, specifically in post-training, fine-tuning, benchmarking, and RAG.
• 5+ years of professional software engineering experience, with focus on clean code.
• Strong analytical skills to solve complex problems and design innovative LLM-based solutions.
• Hands-on mentality with a pragmatic approach to implementing impactful solutions.
• Proficiency in TypeScript and experience in other industrially relevant programming languages.
• Proven ability to work effectively in cross-functional teams.

Preferred Qualifications:

• Experience in LLM code generation or code analysis.
• Experience in programming language design, compilers, and runtime systems.
• Experience in engineering of vibe coding platforms.

About DFINITY and the Internet Computer: