AI Application Engineer

About the role:

The AI Application Engineer bridges the gap between advanced AI capabilities and practical software implementation. This role focuses on embedding pre-trained large language models, intelligent agents, and RAG systems into production-grade applications, enabling natural language reasoning, automation, and data-driven interactions across business platforms. This role is more focused towards applied engineering of intelligent systems rather than core machine learning development.

Responsibilities: 

• Design and implement AI-driven features powered by LLMs, vector search, and retrieval-augmented generation techniques
• Build, integrate, and orchestrate intelligent agents capable of reasoning and autonomous task completion using frameworks such Azure AI Foundry, Google Vertex AI, Amazon Bedrock or LangChain
• Connect AI models and agents with APIs, external tools, knowledge bases, and databases to support dynamic workflows
• Develop backend services and microservices that interact efficiently with model endpoints (e.g., OpenAI, Anthropic, Azure OpenAI, Gemini or other cloud or local models)
• Prototype and productionize AI copilots, assistants, and chat interfaces within enterprise or SaaS environments.
• Implement retrieval mechanisms using vector databases (e.g., Azure AI Search, Pinecone, FAISS, Milvus) to enable contextual grounding of language model outputs
• Collaborate with product and UX teams to align AI integrations with user needs and ensure reliable, explainable system behavior
• Monitor AI-driven services for latency, cost efficiency, and performance consistency in real-world deployment
• Maintain documentation for AI integration frameworks, agent logic, and deployment architectures
• Lead the development and deployment of AI applications, managing the full lifecycle from ideation to production 
• Mentor junior engineers, providing guidance and support to enhance team performance and technical prowess

What we are looking for: 

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, AI, or a related technical field
• Strong programming experience with at least one of the following languages: Python, TypeScript or Node.js, Java
• Familiarity with modern LLM frameworks and toolkits: Semantic Kernel Agent Framework, Azure AI Foundry Agent Service, LangChain, LlamaIndex, etc
• Practical understanding of vector search, RAG design, and prompt engineering
• Experience with cloud AI platforms (Azure AI Services, AWS Bedrock, or GCP Vertex AI)
• Proven experience integrating APIs and deploying AI-based microservices
• Robust knowledge of REST, GraphQL, and event-driven architecture
• Ability to reason about agent workflows, state management, and orchestration logic

Nice to have:

• Experience with building conversational frontends (e.g., web chat UIs, Microsoft 365 Copilot plugins, Slack/Teams bots)
• Understanding of model evaluation, safety mechanisms, and hallucination prevention
• Hands-on experience with cloud platforms, such as Azure, GCP, AWS
• Hands-on experience with popular LLMs, such as GPT, Gemini, Claude, including the ability to fine-tune and optimize these models for specific use cases
• Familiarity with containerization (Docker, Kubernetes) and CI/CD practices
• Experience using monitoring tools for agent observability (e.g. Azure AI Foundry Observability, Langfuse, Prometheus, OpenTelemetry)
• Eagerness and ability to learn new skills and solve problems
• Contributions to open-source agentic or LLM integration frameworks or a portfolio of projects (e.g., GitHub repository) demonstrating practical experience in building applications with LLMs, agents, or RAG systems is highly desirable