Role & responsibilities

CredBuddha is looking for a Python AI/LLM Engineer with 34 years of experience in Python,

AI/LLM integration, GPU servers, PostgreSQL, and production deployments. The role involves deploying open-source LLMs (Qwen/Llama), building APIs, managing AI infrastructure, and supporting scalable AI applications.

1. GPU Server Management

- Set up, configure, and maintain GPU servers for AI workloads.
- Manage NVIDIA GPU drivers, CUDA, GPU memory, and related dependencies.
- Monitor GPU utilization, VRAM consumption, and system performance.
- Troubleshoot GPU-related issues, CUDA errors, and out-of-memory problems.
- Optimize GPU resources for effective model inference.

1. LLM Deployment and Chatbot Integration

- Deploy, configure, and run Qwen and other open-source LLMs on GPU servers.
- Use inference frameworks such as vLLM, Ollama, or Hugging Face Transformers.
- Integrate LLMs with chatbot applications and backend services.
- Optimize model inference performance, concurrency, and memory utilization.
- Troubleshoot model-loading failures and inference performance issues.

1. Python Backend Development

- Develop and maintain backend applications using Python.
- Build REST APIs using FastAPI or Flask.
- Integrate LLM inference services with backend applications.
- Implement error handling, logging, validation, and API testing.
- Write clean, efficient, and maintainable code.

1. Database Management

- Work with PostgreSQL and SQL for application data management
- Design and maintain database schemas, tables, relationships, and indexes.
- Write and optimize SQL queries.




- Troubleshoot database performance issues.
- Manage database connections, transactions, backups, and data integrity.

1. Application Deployment and Production Support

- Deploy Python applications and AI model-serving services on Linux servers.
- Use Docker and Docker Compose for containerization and deployment.
- Configure application environments, networking, and service management.
- Monitor application logs, system health, and resource utilization.
- Troubleshoot production issues and ensure service reliability.
- Maintain deployment documentation and operational procedures.

Required Technical Skills
- Strong hands-on experience with Python programming.
- Experience with FastAPI or Flask and REST API development.
- Practical experience deploying and running Qwen or similar open-source LLMs.
- Hands-on knowledge of GPU servers, NVIDIA GPUs, CUDA, and VRAM management.
- Good knowledge of PostgreSQL and SQL query optimization.
- Experience with Linux server administration and shell commands.
- Experience with Docker and application deployment.
- Knowledge of Git, debugging, logging, and production troubleshooting.
- Experience maintaining production AI applications.

Experience and Expectations
- 34 years of relevant hands-on technical experience.
- Ability to independently handle development, deployment, and troubleshooting.
- Ability to investigate issues across GPU infrastructure, LLM serving, Python APIs, and

PostgreSQL.
- Strong problem-solving skills and ownership of assigned responsibilities

Preferred candidate profile

📌 Python AI/LLM Engineer( GPU Server & Deployment) (Hyderabad)
🏢 Intexm Media
📍 Hyderabad