On-site - Longevity AI HQ, Tel Aviv, Israel

• Full-time
  
  

About The Position

Longevity AI is on a mission to give everyone more healthy and happy years.

We are building a medical-grade, evidence-based operating system for proactive healthcare. For medical teams, the Longevity Dashboard helps predict and prevent the chronic diseases of aging, which are responsible for most of our unhealthy years. For members, the Longevity App turns clinical, biomarker, wearable, and lifestyle data into personalized plans that adapt over time and suggest the actions with the highest potential impact on health.

Our work sits at the intersection of medicine, machine learning, and product engineering. We partner with leading health organizations and work with complex clinical data, including biomarkers, imaging, wearables, and longitudinal health records. The stakes are real: when our AI systems support a clinical conversation, accuracy, traceability, and safety are not optional.

We are looking for an AI Engineer to help build the AI systems behind our conversational clinical assistant and the evidence-grounded retrieval layer that keeps its answers accurate, cited, and clinically useful.

The Role

You’ll help build AI that clinicians trust in real patient care. Every improvement you make has the potential to influence preventive care at national scale and ultimately extend healthy human life.This includes building the conversational AI assistant, improving retrieval over trusted medical and scientific sources, connecting AI workflows to live patient data, and creating the evaluation infrastructure that allows us to measure quality before we ship.

This is a hands-on engineering role. You will work closely with Data Science, Backend, Product, and clinical experts to turn complex medical logic into reliable AI product experiences.

What You’ll Do

• Build and extend our conversational clinical AI assistant, enabling healthcare professionals to ask complex clinical questions and receive accurate, evidence-grounded answers.
• Develop and harden our RAG system using trusted medical and scientific sources, embeddings, vector retrieval, smart chunking, ranking, and citation-aware generation.
• Design agentic AI workflows that combine patient data, medical evidence, internal tools, and clinical logic into reliable product features.
• Own AI quality by building evaluation suites for accuracy, safety, citation faithfulness, regression testing, and clinical reliability.
• Optimize LLM-powered features for latency, cost, observability, and production stability.
• Collaborate with Data Science and Backend teams to translate biomarker models, disease-risk logic, and clinical workflows into scalable AI systems.
• Help define engineering standards for building AI in a regulated, high-trust healthcare environment.
• Support our Data Science team to help train, refine, and serve our models
  
  

Must-Haves

• 3+ years of professional software engineering experience, including meaningful experience building and shipping production AI, ML, or LLM-powered systems.
• Strong Python skills and solid backend/API engineering experience.
• Experience with REST APIs, async systems, SSE, WebSockets, and HTTP streaming.
• Hands-on experience building LLM applications such as RAG systems, agents, tool-calling workflows, or multi-step AI pipelines.
• Working knowledge of vector databases, embeddings, retrieval strategies (RAG/KAG, MCP), agent skills, and prompt orchestration.
• A strong evaluation mindset: you measure AI quality with evals, regression checks, and structured testing - not just manual prompt review.
• Ability to communicate clearly and collaborate across engineering, data science, product, and clinical stakeholders.
• Comfort working in a fast-moving startup environment where ownership, judgment, and execution matter.
  
  

Nice-to-Haves

• Experience in health-tech, medical, clinical, or regulated-data environments.
• Understanding of clinical validation, patient-data sensitivity, HIPAA/GDPR, or the risks of building AI for medical workflows.
• Experience with LangChain, LangGraph, or similar AI orchestration frameworks.
• Familiarity with LLM evaluation, monitoring, observability, and tracing tools.
• Background that bridges computer science and biology, bioinformatics, medicine, or health data.
  
  

Why Join

You will work on AI where correctness genuinely matters.

This role is not about running experiments on the side. You will help build core AI product infrastructure: the clinical assistant, retrieval quality, citations, evaluations, and the systems that determine whether our AI can be trusted in real healthcare workflows.

The challenge is not getting an LLM to produce an answer. The challenge is making it accurate, grounded in evidence, measurable, fast, safe, and clinically useful-even when the underlying medical data is messy, incomplete, and constantly evolving.

You'll work across the full AI stack, from retrieval and agent orchestration to evaluation, prompt engineering, and production infrastructure. You'll help define how modern AI should be built for healthcare, where reliability matters as much as intelligence.

If you're excited by difficult engineering problems, shipping quickly, and building technology that can improve how medicine is practiced, we'd love to talk.

Join us.