Role Overview
The AI Engineer will be responsible for designing, building, and operating production-grade AI services. This role focuses on backend engineering, system architecture, and reliable deployment of AI capabilities at scale, working closely with AI Specialists to bring research and prototypes into real-world applications.
Key Responsibilities
· Design and implement backend services and microservices supporting AI-driven products
· Build and maintain high-performance APIs using FastAPI for AI services
· Integrate Large Language Models (LLMs) and agentic AI workflows into production systems
· Develop clean, maintainable, and well-structured code following established design patterns
· Design and manage data persistence layers using SQLAlchemy and relational databases
· Deploy, operate, and monitor AI systems on AWS
· Implement and maintain CI/CD pipelines for AI services
· Collaborate with cross-functional teams to deliver robust AI solutions
· Ensure scalability, reliability, security, and cost efficiency of AI services
Required Qualifications
· Strong experience with Python and backend software development
· Proven experience designing and working with microservices architectures
· Hands-on experience integrating and using LLMs in applications
· Solid understanding of software design patterns and clean code principles
· Experience with Docker and cloud environments (AWS preferred)
· Familiarity with CI/CD pipelines and production monitoring practices
· Strong problem-solving skills and attention to detail
Preferred Qualifications
· Master’s degree or advanced specialization in AI/ML
· Experience with agentic AI frameworks (e.g., LangChain, LlamaIndex, CrewAI)
· Familiarity with LangChain, LlamaIndex, and Retrieval-Augmented Generation (RAG) frameworks
· Exposure to MLOps practices and inference optimization
· Background in industrial-scale or complex enterprise AI implementations