AI Application Engineer

Generative AI Application Engineer

At I-Next Data, the AI innovation center of Tel Aviv Sourasky (Ichilov) Medical Center, we build and deploy cutting-edge AI systems that directly support clinicians and patients. Our mission is to translate LLMs and scalable data platforms into clinical reality. We are a 30+ developer team focused on production, within a group of ~40 employees.

We’re seeking a generative AI application engineer for a new GenAI team. You will deploy and serve proprietary language models on Amazon Bedrock and Azure OpenAI. In this role, you’ll automate data pipelines, embed evaluation frameworks, and own the observability stack, delivering low-latency, cost-efficient generative AI services that scale from prototype to production.

Key Responsibilities

· Deploy models via APIs, Bedrock, Azure OpenAI or self-hosted LLMs; containerize and monitor (Docker, K8s, LangFuse, Phoenix) with support from our dedicated DevOps team.

· Build user-facing systems (e.g., summarization tools, design assistants…) using Python.

· Orchestrate multi-step pipelines: prompt → retrieval (RAG) → generation → evaluation → feedback loop.

· Develop and integrate evaluation frameworks with custom metrics.

· Optimize latency vs accuracy, cost per 1K tokens, and context-window management.

Skills and Experience

· 4+ years of experience in software development and strong Python programming skills.

· Design thinking and problem-solving mindset.

· Frameworks & orchestration: LangChain / LangGraph, Docker/Kubernetes.

· Evaluation & benchmarking: G-Eval, HealthBench, LLM-as-a-Judge.

· Deployment: AWS Bedrock, Azure.

· Work with data vector DBs, feature stores.