Senior Genai Engineer (Remote)

OverviewIn this senior role, you will design and scale genAI workflows to power a next-generation coverage analysis platform. You’ll architect agentic, multi-step systems and integrate diverse LLM providers for production-grade AI solutions. You’ll work across teams to refine prompts, improve performance, and drive the platform’s evolution. This is an opportunity to shape how AI capabilities deliver business value at scale in a global, innovative environment.Compensaciones / Beneficios 100% remotecompetitive compensationglobal enterprise environmentcareer growth and technical leadership opportunitiesexposure to cutting-edge AI projectsResponsabilidades Architect GenAI workflows with modular, composable steps using LangGraphBuild and manage LLM orchestration layers with tools like LiteLLMCreate typed data flows and validation with PydanticEvaluate and integrate multiple LLM providers (OpenAI, Claude) for latency, cost, and qualityImplement observability, logging, tracing, and monitoring with Langfuse or LangSmithOptimize prompts, token usage, and inference efficiencyCollaborate with data scientists, AI engineers, and product teams to refine prompts and deploy featuresRequisitos principales 5+ years of Python development2+ years building production systems powered by LLMsHands-on experience with LangGraph or similar frameworksDeep expertise with Pydantic for data modelingStrong understanding of LLM capabilities, prompts, and evaluationProduction experience with async Python (asyncio)Ability to design complex architectures with minimal guidancecross-functional collaborationinitiative and ownershipstrong communicationLangGraph or LangChainLiteLLM or multi-model layersPydantic

Requisitos principales 5+ years of Python development 2+ years building production systems powered by LLMs Hands-on experience with LangGraph or similar frameworks Deep expertise with Pydantic for data modeling Strong understanding of LLM capabilities, prompts, and evaluation Production experience with async Python (asyncio) Ability to design complex architectures with minimal guidance cross-functional collaboration initiative and ownership strong communication LangGraph or LangChain LiteLLM or multi-model layers