Backend AI engineer

About the Role

We are looking for a Senior AI Engineer to join a growing team focused on building and deploying cutting-edge AI solutions in production environments.

This role combines software engineering, cloud development, and Generative AI, requiring a hands-on professional capable of designing, developing, deploying, and maintaining end-to-end AI-powered applications.

You will work closely with AI Engineers, Data Scientists, and Front-End Developers to build scalable and reliable solutions leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and cloud-native Azure services.

Key Responsibilities

• Design, develop, and maintain scalable backend services and APIs using Python.

• Build and deploy enterprise-grade AI solutions on Microsoft Azure.

• Integrate Large Language Models (LLMs) and Generative AI capabilities into production applications.

• Design and implement Retrieval-Augmented Generation (RAG) architectures.

• Develop prompt engineering strategies and optimize LLM interactions for business use cases.

• Build intelligent document processing solutions leveraging LLMs and AI services.

• Integrate capabilities such as semantic search, document understanding, speech-to-text, and AI agents.

• Collaborate with cross-functional teams to ensure seamless integration of AI services and applications.

• Monitor performance, troubleshoot production issues, and continuously improve solution reliability and scalability.

• Contribute to technical architecture decisions and challenge existing implementations to improve code quality and maintainability.

• Stay up to date with emerging trends and innovations in Generative AI, LLMs, and AI engineering.

Required Experience & Skills

Technical Skills

• Strong software engineering background with extensive experience in Python.

• Experience developing backend applications, microservices, and REST APIs.

• Proven experience working with Large Language Models (LLMs) and Generative AI solutions.

• Hands-on experience with Prompt Engineering beyond basic prompt creation.

• Experience designing and implementing Retrieval-Augmented Generation (RAG) solutions.

• Knowledge of NLP concepts such as embeddings, semantic search, document understanding, and entity extraction.

• Experience deploying and managing cloud solutions on Microsoft Azure.

• Understanding of AI solution lifecycle, deployment, monitoring, and optimization.

Nice to Have

• LangChain, LlamaIndex, Semantic Kernel, or similar AI orchestration frameworks.

• Intelligent Document Processing (IDP).

• OCR and document extraction technologies.

• Speech-to-Text solutions.

• AI Agents and agentic workflows.

• Node.js development experience.

• Microsoft Bot Framework.

• Docker and containerized deployments.

• CI/CD and DevOps practices.

Interested in learning more? We'd love to hear from you. Reach out and let's schedule a conversation to discuss the opportunity.