Lead LLM Engineer, Full Stack

We’re seeking a mission‑driven Lead LLM engineer to join our incredible engineering team at Cairns Health. The role sits at the crossroads of voice‑driven healthcare and ambient sensing, using conversational AI, radar, and sensor fusion to empower patients to “use their voice” to engage more actively in their health and wellness. A key part of our experience is our digital health and lifestyle assistant Luna, who interacts daily with our users, building trust and rapport, simplifying complex care plans into behavioral nudges, and engaging seniors and their loved ones to address social isolation, loneliness and more!

You’ll play a pivotal role in the success of our product, including managing and innovating our LLM architecture to ensure we are always delivering a best‑in‑class experience with low latency, high empathy, and always useful engagement. You will also work side by side with our prompt‑engineering team to continuously add more features that reduce friction for our users and increase the value of the platform through making their lives easier and supporting their health journey.

• Manage and maintain LLM infrastructure with appropriate guardrails to ensure we are maximizing access to features that can be delivered consistently and on‑persona while mitigating hallucinations
• Design and implement appropriate architecture to ensure performance, including constellations with failover capabilities
• Daily coding and weekly code reviews with CTO
• Daily collaboration with prompt‑engineering team to drive pipeline of new features to staging and production environments
• Optimize our LLM applications for latency, concurrency, uptime, and other key metrics
• Collaborate with a team of accomplished, high‑performing engineers

• Bachelor’s degree in Computer Science, Engineering, or a related field or equivalent practical experience, coupled with 3–5 years of professional experience as a Full‑Stack Software Engineer or in a similar role
• 3 years professional experience in LLM architectures (e.g., RAG, constellations, etc.) is a must
• Familiarity with commonly used LLM APIs (OpenAI, Gemini, Claude, etc.)
• Familiarity with modern Voice AI application stacks (STT, LLM, TTS models) desired
• Proficient in Python and Java 11+ for developing robust server‑side applications and experienced in designing and implementing RESTful APIs to facilitate seamless integration between front‑end and back‑end systems
• Hands‑on experience with Postgre
  
  SQL or other relational databases, ensuring efficient data storage, retrieval, and management for scalable applications
• Proficient in containerization using Docker and orchestration with Kubernetes, with a proven track record of deploying and managing applications on AWS EKS and ECS
• Familiarity with messaging systems like Kafka and MQTT for real‑time data processing and communication, along with proficiency in using Git Hub for version control and collaborative development
• Experience implementing and managing CI/CD pipelines using Git Hub Actions or similar tools, familiarity with Agile/Scrum methodologies for iterative and collaborative software development, and strong problem‑solving and analytical abilities to tackle complex technical challenges
• Positive, team player with strong people skills and excellent communication

We offer competitive compensation, equity, and benefits – including medical, dental, vision, paid vacation/sick days, and 401(k) plans.

Preference:
Local to Sunnyvale, CA. We are an office‑based organization. Will consider remote/hybrid for the right candidate.

Cairns Health is creating a fundamentally better healthcare experience for people with chronic health conditions and those who care for them. We make healthcare more accessible by simplifying complex care plans, connecting care teams, and meeting patients where they live. Through our conversational AI, patients use their voice to interact with our digital care companion, who proactively gives medication reminders, symptom checks, behavioral nudges, and even engages in friendly conversation to ease loneliness.

Cairns uses a device that includes radar to put the patient in context and passively monitors their activities, including heart rate, breathing rate and sleep stages, all without a wearable. The result is informed and timely intervention that drives improved clinical outcomes, reduced care delivery costs, and a more satisfactory healthcare experience for all.

Please send your resume and cover letter to: anya.

Mid‑Senior level

Full-time