About the company
Elixi is an AI-driven HealthTech startup with a mission to democratize long-term health by transforming scattered data into insights and recommendations people can trust and act on. We’re led by a successful tech entrepreneur who has built a global decacorn ($10B+) before — and has the ambition and resources to do it again.
This is a chance to join early and directly influence what we build, how we build it, and the culture we create along the way. We operate as a small, relentless team with strong ownership and high standards — if you’re driven to achieve greatness and grow alongside ambitious peers, you’ll feel at home.
About the role
We are seeking a highly skilled and motivated LLM Engineer to join our dynamic health tech startup. In this role you will play a crucial role in analysing user data, developing predictive models, and creating innovative algorithms that drive our platform's functionalities.
What you'll be doing
- Develop and maintain the orchestration layer.
- Integrate and fine-tune prompts for various LLM providers (OpenAI, Anthropic, open-source models), optimizing for cost, latency, and accuracy.
- Implement Function Calling to allow the AI to interact with external APIs and internal services and databases.
- Manage Vector Databases for efficient semantic search of medical data.
- Build guardrails and validation modules to filter out unsafe or medically incorrect advice before it reaches the user.
- Work closely with Product, Science to achieve high-quality of the solution; Backend Engineers to deploy these AI modules as scalable microservices.
What you'll need
- Bachelor’s degree in a quantitative discipline (Mathematics, Statistics, Computer Science, Engineering); Master’s or PhD is a significant plus.
- 5+ years proven experience in Data Science.
- Proven experience building applications with LLM APIs (OpenAI, Anthropic, Google) and orchestration frameworks (LangChain, LangGraph, LlamaIndex, or DSPy or others).
- Deep understanding of RAG systems: chunking strategies, embedding models, vector search, and re-ranking algorithms.
- Proficiency in Python, Strong SQL skills for querying and managing large datasets.
- Solid understanding of statistics with the ability to evaluate model performance effectively.
- Experience with Prompt Engineering techniques and structured outputs.
- Ability to write modular, testable code for production environments.
- Ability to communicate complex data findings to non-technical stakeholders clearly.
- Strong problem-solving skills with a proactive approach to data challenges.
Nice to have
- Experience with data manipulation libraries (Pandas, NumPy) and machine learning frameworks (TensorFlow, PyTorch).
- Experience in deploying open-source models.
- Familiarity with cloud platforms (AWS, Google Cloud, Azure) for deploying models and managing data pipelines.
- Understanding of DevOps practices, including version control (Git) and CI/CD.
- Knowledge of gamification principles for designing engaging user experiences.
What we offer
- Meaningful ownership and a real impact on the product
- 30 working days of annual leave, plus an extra day off on your birthday
- Comprehensive medical insurance
- Team offsites and events 1-2 times a year
- Home office budget to help you create a comfortable and productive workspace
- Personal longevity & learning budget to invest in your health, wellbeing, and professional development
