Senior Data/AI Engineer
Core
Architect and build scalable Generative AI-powered systems, including LLM applications and research agents, to underpin a next-gen research enablement platform.
Role type
Senior IC Generative AI Engineer (LLM/RAG)
Builds
Production-grade AI/ML systems, RAG pipelines, and research agent copilots
Domain
Healthcare research enablement / Generative AI
Deliverable
production ML models
Required skills
Python, backend frameworks (FastAPI/Flask), asynchronous programming, distributed system design, CI/CD, containerization (Docker), orchestration (Kubernetes/Helm), LLM application development, RAG pipeline optimization, vector databases (Pinecone/Elasticsearch), prompt engineering, AI system evaluation, large-scale data processing (Databricks/Spark), LLM frameworks (LangChain/LlamaIndex)
Preferred skills
Azure cloud platform expertise, experience with LLM Judges/MLflow for observability
Technologies
Databricks, Azure Kubernetes Service (AKS), FastAPI, LangChain, Pinecone, MLflow
Responsibilities
Design and operate low-latency backend services and APIs for Generative AI features; own the end-to-end lifecycle of AI applications from design to production monitoring; optimize retrieval and generation quality in RAG pipelines; engineer solutions integrating LLMs with proprietary knowledge repositories; establish LLMOps best practices including automated evaluation and observability; evaluate and implement advanced prompt engineering methods; provide technical leadership and mentorship to junior engineers; partner with stakeholders to define technical priorities and roadmap.
Seniority
Senior, hands-on IC with mentorship responsibilities