• Develop, optimize, and maintain AI/LLM models, prompts, pipelines, and vector-based search

• Evaluate models, improve accuracy, and ensure outputs meet scientific and operational expectations

• Contribute to high-level architectural decisions and ensure optimal performance, speed, and cost efficiency across AI and backend systems

• Collaborate closely with product, DevOps and engineering teams to deliver features with enterprise quality

• Participate in technical incident analysis and support root-cause investigations when needed

• Engage in technical discussions with enterprise clients

Qualifications

• 2 years of experience in LLM engineering or equivalent academic background

• Master’s degree (or higher) in Data Science, Computer Science, or a related technical field.

• Proficient coding skills in Python

• Strong experience with LLMs, embeddings, vector databases, GenAI, and text-heavy AI workloads

Bonus Skills

• Experience with RAG or LLM-augmented workflows

• Familiarity with semantic modelling and structured content systems

• Strong understanding of SaaS architecture and performance optimization

What We Offer

• A high-impact technical role building the core AI/architecture behind Protocol AI

• Opportunity to contribute to the future of an end-to-end digital study design and protocol development ecosystem