What You'll Do

As an AI Engineer on our team, you will take ownership of end-to-end AI solution delivery, from initial concept through production deployment and ongoing optimization. You'll architect and implement LLM-powered applications & enrichments, multi-agent workflows, and autonomous AI systems that directly impact our users' experiences. Your work will involve orchestrating large language models, building sophisticated prompt engineering frameworks and fine-tuning.

You'll be responsible for deploying and operating these LLM applications at scale, ensuring they perform reliably in production environments. This includes containerizing AI services, implementing deployment pipelines for rapid iteration, and establishing monitoring systems that track both performance metrics and AI-specific indicators like response quality, hallucination rates, and autonomous decision accuracy.

Your role encompasses ensuring our AI systems are production-ready and enterprise-grade. You'll manage the infrastructure that powers our AI applications, optimizing for both performance and cost-effectiveness, establishing automated evaluation frameworks for LLM applications, and building robust fallback mechanisms. You'll ensure our AI systems meet security and compliance requirements while maintaining the ability to rapidly iterate and improve AI capabilities based on user feedback and performance data.

What You'll Bring

• 5+ years of hands-on experience in AI/ML engineering, software development, or related technical roles with demonstrable experience building and deploying AI-powered applications
• Good theoretical knowledge of AI, ML and NLP principles as demonstrated by a bachelor's or master's degree in computer science or equivalent degree.
• Strong programming proficiency in Python and familiarity with Java/Kotlin, with a solid understanding of API design, development and integration patterns
• 
  

LLM and Generative AI Expertise

Experience with frameworks such as LangChain, LangGraph, and APIs from OpenAI, Anthropic, etc.

Demonstrated proficiency in prompt engineering and orchestrating AI agents, chatbots, and autonomous workflows

Cloud, Deployment & Operations Experience

• Familiarity with cloud AI/ML services (Azure preferred, also AWS or Google Cloud), container orchestration (Docker, Kubernetes), CI/CD deployment pipelines, automated testing for LLM applications, infrastructure monitoring, logging, and performance tracking
• Strong problem-solving abilities with experience debugging AI systems, optimizing performance bottlenecks, and implementing scalable solutions
• Collaborative mindset with excellent communication skills to work effectively with cross-functional teams in an agile environment, including product managers, data scientists, and platform engineers
• Continuous learning orientation with demonstrated ability to quickly adopt new AI technologies, frameworks, and best practices in this rapidly evolving field
• 
  

Nice to Have

• Knowledge of vector databases and RAG (e.g., OpenSearch, ElasticSearch) for semantic search and knowledge retrieval
•