Generative AI Engineer

Job Title: AI Engineer

Experience: 2–6 years overall (with 1+ years in AI application development, LLM integrations, or cloud-based AI solutions)

Role Overview

We are seeking an AI Engineer to build and implement AI-powered applications across enterprise use cases such as intelligent assistants, automation, search, recommendation, and workflow enhancement. The ideal candidate will be a hands-on engineer who can work with modern AI services, LLM frameworks, cloud platforms, and backend systems to deliver scalable, secure, and production-ready AI solutions.

This role bridges product needs and technical execution by translating business requirements into working AI features, reusable services, APIs, and workflows that can be deployed across products and teams.

Key Responsibilities

• Build and deploy AI-powered applications and services using Python, APIs, and cloud-native components across Azure and AWS.
• Integrate LLMs and AI services into enterprise applications for use cases such as copilots, chatbots, document intelligence, search, and automation.
• Implement retrieval-based AI patterns such as RAG using enterprise data sources, embeddings, and vector databases.
• Develop and maintain backend workflows, service layers, and API integrations required to operationalize AI capabilities in production.
• Collaborate with AI Architects, product teams, data teams, and business stakeholders to convert use cases into scalable technical solutions.
• Support deployment, monitoring, logging, and optimization of AI applications for performance, reliability, and cost efficiency.
• Follow engineering best practices for version control, CI/CD, containerization, and documentation across AI solutions.
• Contribute to reusable components, templates, and implementation standards for AI engineering across teams.

Required Skills

Engineering & Development

• Strong Python programming skills with experience in backend development, APIs, and system integration.
• Good understanding of software engineering fundamentals including Git, code versioning, testing, and deployment practices.

AI Applications & LLMs

• Hands-on experience building or integrating AI-powered applications using LLM APIs or cloud AI services.
• Familiarity with prompt design, context handling, and enterprise AI application patterns such as chatbots, copilots, or search assistants.

Cloud & Platform

• Working knowledge of Azure and/or AWS services such as compute, storage, serverless, and AI services.
• Experience deploying applications or services in cloud environments.

MLOps / Deployment Foundations

• Familiarity with CI/CD pipelines, Docker, and basic deployment workflows for AI or backend applications.
• Exposure to monitoring, logging, and production support for enterprise applications.

Preferred Qualifications

• Experience with LangChain, LlamaIndex, Semantic Kernel, or similar orchestration frameworks.
• Exposure to vector databases, embeddings, and enterprise knowledge retrieval patterns.
• Basic understanding of ML concepts sufficient to work with data science or ML teams when needed.
• Experience building internal enterprise AI tools or customer-facing AI features.

Why Join Donyati

At Donyati, we don't just implement technology — we help clients accelerate intelligent business transformation through practical, scalable, and high-impact solutions. You'll work alongside experienced architects and engineers, gain hands-on exposure to enterprise AI delivery, and help build modern AI capabilities that create measurable business value.