GenAI Engineer

We are seeking a GenAI Engineer to lead the end-to-end development, deployment and operation of enterprise-grade AI-powered applications. The role combines backend engineering, LLM integration, cloud infrastructure and AI platform operations to deliver scalable GenAI solutions in production environments. You will work closely with AI/DS, Product and DevOps teams to build and scale AI-driven applications, ensuring reliability, observability, performance optimization and operational excellence across the full AI SDLC. The role also includes contributing to GenAI-assisted development practices, scaling enterprise AI SDLC processes, supporting AI Beauty Chat initiatives through agentic micro-pod delivery models and performing System Steward responsibilities across AI platform initiatives. Responsibilities Design, develop, deploy and maintain backend services for AI/LLM-powered applications Own E2E delivery of GenAI features from implementation to production support Integration and operation of LLM APIs (e.g. OpenAI) in enterprise production environments Development of APIs, orchestration layers and microservices supporting agentic AI workflows Optimization of LLM systems for latency, resiliency, retries, fallbacks and cost efficiency Implementation of CI/CD pipelines, observability, monitoring and logging for AI services Collaboration with AI/DS, Product, DevOps and platform teams to streamline delivery and improve reliability Work with Azure cloud environments and distributed systems (Redis, Kafka, SQL/NoSQL) Support for MCP integrations, agentic memory initiatives and AI orchestration frameworks Drive GenAI-assisted development practices and scale AI SDLC processes Contribution to AI Beauty Chat delivery through agentic micro-pod execution models Execution of System Steward responsibilities in agentic micro-pods Requirements 2+ years of Python backend engineering experience Expertise in building and operating production-grade GenAI/LLM applications end-to-end Hands-on experience with OpenAI or other LLM APIs in production Proficiency in prompt engineering, agentic workflows and orchestration patterns Capability to handle LLM operational challenges: latency, retries, fallbacks, observability and cost optimization Strong understanding of scalable backend and distributed system architecture Skills in CI/CD, DevOps workflows and Azure cloud environments Background in applying GenAI across the SDLC (AI-assisted development, testing, deployment and delivery workflows) Working knowledge of SQL/NoSQL databases, Redis and Kafka Familiarity with Databricks and MCP Excellent English communication skills (B2+ level)