GenAI Ops Engineer

GenAI Ops Engineer

Istanbul

Artificial Intelligence – MLOps /

Remote

Apply for this job

Lyrebird Studio is a top mobile app development company produce user-friendly entertaining mobile apps for Android and iOS. Lyrebird takes firm steps for the future with its 45 million monthly active users and more than 2 Billion+ total downloads and installs over the globe. Its creative, technical and design teams work with passion and devotedly to meet the mobile app users expectations.

You will join an organic structure where you will take ownership of your role and contribute actively with new ideas of new projects in a creative and stimulating working environment. You will be part of a small and high performing team and you will work together in goodwill to achieve best results.

Feel free to think big and if you're up to the challenge, come and join us!

We are looking for talent interested in creating something bigger! To succeed in this role, you will need to have a good understanding of the casual mobile apps market.

You will join a dynamic working environment where small teams can form around ideas.

Your Profile

• Bachelor’s degree in Computer Engineering, Software Engineering, AI Engineering or related field
• 1+ year of experience in software/infrastructure development & operations with a focus on CI/CD, orchestration, and release tooling
• Proficient with AWS Cloud services and infrastructure-as-code using AWS CDK
• Strong Python skills with hands-on experience in deep learning frameworks like PyTorch and TensorFlow
• Experience with Docker and Kubernetes for containerized GPU inference on AWS
• Familiarity with building and maintaining large-scale GPU-based services
• Fluent in English
• Agile, self-driven, analytical, result-oriented and a strong team player

Nice to Have

• Experience with diffusion-based image generation models (e.g., Stable Diffusion, DALL·E, Midjourney)
• Expertise in monitoring, observability and performance tuning for GPU-heavy services—tracking latency, error rates and utilization

Responsibilities

• Build, deploy and maintain scalable image-generation APIs handling millions of GPU-powered inference requests daily
• Design CI/CD pipelines for model training, fine-tuning and production deployment using AWS CDK
• Containerize and orchestrate inference services using Docker and Kubernetes
• Implement monitoring dashboards to track GPU usage, inference latency, error rates, and model output quality
• Collaborate with research and engineering teams to integrate model checkpoints and update pipelines
• Automate infrastructure provisioning with AWS CDK and ensure production reliability
• Troubleshoot production issues and continuously optimize system performance

Working at Lyrebird

• You will be working in one of the best and first mobile product company in Turkey, working on a global level and recognized internationally.
• Flat hierarchies and short decision-making procedures; we live the well-known start-up atmosphere – you’ll find the direct contact person for any matter easily within reach
• Taking responsibility from day one, improve your skills and learning continuously
• An absolute sense of unity; together we are aiming for the same goal – you’ll be part of the company's success
• Fast-paced environment with a tight-knit and collaborative culture.
• Never-ending learning and development opportunities.
• Unlimited fruits, snacks, coffee and tea at the office.
• Remote working opportunity.

Apply for this job