Applied AI Engineer - Python

Role Summary :

The Applied Engineer will work on building and scaling GenAI-driven conversational applications, with a strong focus on backend development, AI agent orchestration, and cloud-native deployments. This role requires hands-on expertise in Python, .NET, and Azure, and the ability to translate GenAI concepts into reliable, production-grade systems.

Key Responsibilities :

- Design, develop, and maintain backend services using Python (FastAPI, Flask) and .NET Core (C#)

- Build, orchestrate, and optimize GenAI agent workflows using LangChain, LangGraph, AutoGen, or similar frameworks

- Develop and expose RESTful APIs for chatbot and backend integrations

- Integrate applications with Azure services including Azure OpenAI, CosmosDB, and Application Insights

- Collaborate with ML engineers to deploy, monitor, and optimize GenAI agents in production

- Implement CI/CD pipelines and support containerized deployments using Docker and Azure DevOps

- Debug, test, and document code with a strong emphasis on scalability, security, and maintainability

- Participate in code reviews and contribute to engineering best practices

- Mentor junior engineers as required and support knowledge sharing

Required Skills :

- Strong proficiency in Python, with hands-on experience using FastAPI, Poetry, and pytest

- Working knowledge of .NET Core, REST APIs, and backend service architectures

- Hands-on experience with GenAI frameworks such as LangChain, LangGraph, AutoGen, or equivalent

- Experience with Azure cloud services, particularly Azure OpenAI and CosmosDB

- Solid understanding of Git workflows, debugging techniques, and unit testing

- Ability to independently understand and work within existing codebases and documentation

Preferred / Good-to-Have Skills :

- Experience with RAG architectures, vector databases, and prompt engineering

- Exposure to CI/CD pipelines, especially Azure DevOps

- Familiarity with frontend frameworks such as Angular or React

- Prior experience working on customer-facing chatbots, conversational AI, or recommendation systems

Key Outcomes :

- Faster delivery of GenAI chatbot features and enhancements

- Improved system reliability and production stability

- Scalable and maintainable GenAI application architecture

- Reduced turnaround time for customer and business-driven changes

(ref:hirist.tech)