Collaborate with cross-functional teams to understand business needs and translate them into backend functionalities for GenAI and Agentic AI projects.
Design, develop, and maintain scalable backend solutions, including event-driven architectures and integration with external systems/APIs.
Manage data storage solutions using relational (PostgreSQL, MySQL) and NoSQL (MongoDB, DynamoDB) databases to support AI applications in production.
Utilize containerization (Kubernetes) and implement DevOps practices, including CI/CD pipelines (Azure DevOps, GitHub Actions), for productive deployment and scalability.
Build and integrate APIs using Python frameworks (Flask, FastAPI) and collaborate with data scientists, engineers, and DevOps teams for seamless AI model deployment.

What You Must Have
At least a Bachelor's & Master's degree
At least 4+ years of experience
Oral and written proficiency in English required

What Sets You Apart
Proficient with LLM interaction frameworks like LangChain, Semantic Kernel, and LlamaIndex,



and experienced in integrating, scaling, and deploying GenAI and agentic applications in production.
Skilled in setting up data pipelines for both model training and real-time inference to support AI workloads efficiently.
Advanced Python expertise including OOP, asynchronous programming (asyncio), concurrency (multithreading, multiprocessing), design patterns, memory management, and performance optimization for scalable GenAI systems.
Solid foundation in data structures, algorithms, software design principles (SOLID, clean architecture), and hands-on experience with cloud-native development on Azure/AWS, including serverless, microservices, and container orchestration (Kubernetes, Docker).
Experience with additional OOP languages (Java, C++, C#) and familiarity with WebSocket implementations for real-time application functionality.

📌 Generative Ai Software Engineer Bengaluru (India)
🏢 PwC
📍 India