Senior / Lead - Software Engineer - Gen AI

Job Description:
We are seeking a highly skilled Senior Python Engineer with extensive experience in FastAPI, microservices architecture, and Generative AI (Gen AI) to join our dynamic team. The ideal candidate will have a strong technical background, proven leadership in technical teams, and expertise in building scalable, resilient, and secure applications with AI-driven capabilities.

Responsibilities:

• Lead the design, development, and deployment of applications using microservice architecture and Gen AI.
• Develop and maintain FastAPI-based backend services with high performance and scalability.
• Integrate Gen AI models to enhance application functionalities.
• Implement best practices in logging, monitoring, health checks, scalability, resilience, service discovery, API gateways, and error handling.
• Ensure code quality, security, and performance optimization.
• Work with containerization technologies like Docker and Kubernetes for application deployment.
• Collaborate with cross-functional teams to define, design, and ship new features.
• Establish and manage CI/CD pipelines for seamless application deployment.
• Implement best practices for API design, development, and security.
• Set up and maintain monitoring and logging tools (e.g., Prometheus, Grafana).
• Ensure adherence to version control systems (e.g., Git) and collaborative workflows.

Preferred candidate profile

• Proven experience in leading technical teams and developing applications using microservice architecture.
• Strong proficiency in Python and FastAPI.
• Deep understanding of Pydantic for data validation in FastAPI.
• Experience with containerization (Docker, Kubernetes).
• Familiarity with CI/CD pipelines and automation tools.
• Knowledge of API design and implementation best practices.
• Experience working with monitoring and logging tools (e.g., Prometheus, Grafana).
• Strong understanding of security best practices in microservices-based applications.
• Experience with Generative AI (Gen AI) and its integration into applications.
• Ability to fine-tune and optimize LLM models for various business applications.

Nice to Have:

• Experience with Retriever models, including implementation of chunking strategies.
• Familiarity with vector databases and their use cases.
• Understanding of optimal approaches in querying LLM models via API.
• Experience with prompt engineering and different strategies for effective interactions with LLMs.
• Exposure to various prompt engineering techniques in different scenarios.