Generative AI Cloud Operations Engineer - Evinova
Core
Design, create, and manage operational excellence for LLM-based agent deployments, multi-agent orchestration, and conversational AI systems pipelines to accelerate science-led innovations in clinical trial design and operational optimization.
Role type
Generative AI Cloud Operations Engineer
Builds
Production-grade agentic Generative AI capabilities for trial management and optimization SaaS product
Domain
Life sciences / Clinical trials / Generative AI
Deliverable
production ML models
Required skills
Generative AI agent deployment, AWS infrastructure, Python/TypeScript, CDK, Docker, Kubernetes, LLM evals tools, RAG pipeline optimization, infrastructure-as-code, CI/CD pipelines
Preferred skills
LangChain, LangGraph, Google ADK, Vertex AI, Azure Foundry, OpenAI, Anthropic, Langfuse, Arize Phoenix, Pinecone, Weaviate, Splunk, Grafana, Prometheus
Technologies
AWS, Docker, Kubernetes, LiteLLM, LangChain, LangGraph, Google ADK, Vertex AI, Azure Foundry, OpenAI, Anthropic, Langfuse, Arize Phoenix, Pinecone, Weaviate, Splunk, Grafana, Prometheus
Responsibilities
Design and implement resilient cloud GenAI agent operational capabilities; Develop and manage GenAI Ops systems for clinical trial design and planning; Integrate LLM proxies/routers; Ensure proper RAG pipeline optimization and scaling; Partner with AI Engineers to transition projects from research to production; Leverage foundation model platforms to provide reliable access to LLMs
Seniority
Mid-level, hands-on IC
