We are looking for a Senior Machine Learning Engineer to build and run production-grade LLM services on Azure. You will turn models and agent workflows into secure, monitored APIs, improve reliability and cost, and partner with data, product and engineering teams to ship AI features that scale.
Apply today and be eligible for a one-month sign-on bonus.
Terms & Conditions apply.
Responsibilities
Productionize AI models, LLM applications and agent workflows into reliable Back-end services and automated pipelines
Build and enhance Python APIs, middleware and integrations connecting user interfaces, AI agents and enterprise systems
Deploy and support solutions across development, test and production with release management and version control
Implement authentication, authorization and access control for AI services, data and files using modern identity patterns
Design resilient systems with observability, robust error handling, retries and failover strategies
Create automated tests across unit, integration and API layers to protect production quality
Monitor model behavior, latency, token usage, operational costs and infrastructure health and act on insights
Optimize scalability and performance through caching, async processing and database tuning
Requirements
Proven experience building Python back-end services with FastAPI, Pydantic, asynchronous programming and pytest
Hands-on experience connecting Azure OpenAI Service or OpenAI APIs including embeddings, tool calling, structured outputs and streaming
Background in LLM observability and telemetry using Langfuse, Grafana or comparable tools
Ability to create orchestration layers for session management, validation, transformation and system integrations
Strong SQL for reusable queries, quality checks, aggregation and analytics-focused data logic
Experience using Azure services such as Azure AI Search, Redis, cloud storage, managed identities and deployment pipelines
Hands-on experience delivering retrieval-augmented generation (RAG) solutions with vector search, hybrid search and ranking techniques
Understanding of security practices including OAuth, Microsoft Entra ID and operational support for distributed systems
Thông tin chung