Senior AI Engineer

About the Role

We're looking for a hands-on AI Engineer to serve as the primary engineering executor for a generative AI platform in production. You'll build and operate AI agents in Azure AI Foundry, help maintain and evolve an internal AI assistant, and support integrations with tools like Copilot Studio — while also keeping a portfolio of classical ML models running smoothly in production.

This is an execution-focused role: you'll take well-defined specifications from the Lead AI Engineer & Architect and ship them independently, asking sharp clarifying questions when architectural decisions aren't yet settled. Documentation is part of the craft here, not an afterthought — you'll be working with a distributed, global team across time zones and need to communicate clearly in written and verbal English.

What You'll Do

• Build and maintain AI agents in Azure AI Foundry — developing new agents from specs and enhancing existing agents already in production
• Support the operation and evolution of the internal AI assistant, including agent integration, prompt iteration, and performance tuning
• Contribute to platform integrations between the internal assistant and adjacent tools such as Copilot Studio, including integrating Copilot Studio agents into Foundry
• Implement the LLMOps framework for generative AI systems — evaluation pipelines, prompt versioning, observability, and cost monitoring — aligned to standards set by the Lead AI Engineer & Architect
• Operate classical ML models in production (classification, regression, time series), including scheduled retraining, performance monitoring, and troubleshooting
• Build monitoring and observability tooling for ML models and AI agents: dashboards, alerts, and operational runbooks
• Partner with QA to ensure models and agents keep meeting quality standards, supporting recurring evaluations as needed
• Write clear technical documentation — code docs, READMEs, operational runbooks, and feature documentation
• Provide first-level technical support for stakeholders using the AI systems, escalating as needed, and occasionally run office-hours-style walkthroughs for non-technical audiences

What We're Looking For

Required:

• 4+ years of experience as an AI Engineer, ML Engineer, or similar role with significant hands-on engineering responsibility
• Hands-on experience building or operating LLM-based systems in production: AI agents, RAG pipelines, prompt engineering, vector stores
• Strong Python skills, including practical experience integrating LLMs via APIs and building production-grade backend services
• Practical experience with at least one major cloud platform for AI workloads (AWS or GCP acceptable, with willingness to learn Azure)
• Working knowledge of classical ML libraries (scikit-learn, XGBoost, pandas, numpy) and the ability to operate existing ML models in production
• Working knowledge of MLOps/LLMOps practices: model versioning, CI/CD for ML, model and agent monitoring, evaluation frameworks, experiment tracking (MLflow or similar)
• Experience deploying and operating AI/ML systems in production environments
• Strong written and verbal communication skills in English
• Comfortable working independently on well-defined tasks while flagging architectural decisions that need input

Nice to Have:

• Familiarity with agent frameworks (e.g., Azure AI Foundry, LangChain, Semantic Kernel)
• Azure experience (Azure ML, Azure AI Foundry)
• Familiarity with Microsoft Copilot Studio, or the ability to ramp up quickly