onsite
LLMOps Engineer - steampunk
Software Engineer
Hands‑on LLMOps Engineer responsible for building, deploying, and optimizing infrastructure and pipelines for predictive and generative AI models, collaborating with AI product engineers and data scientists.
About the role
Key Responsibilities
- Design, implement, and maintain scalable infrastructure for large language model training and inference using Kubernetes and Docker.
- Develop CI/CD pipelines to automate model deployment, versioning, and monitoring.
- Collaborate with AI product engineers and data scientists to integrate LLMs into production services.
- Monitor performance, cost, and reliability of LLM workloads, applying optimizations and troubleshooting issues.
- Ensure security and compliance of AI pipelines, including access controls and data handling.
Requirements
- Strong programming experience in Python and familiarity with ML frameworks.
- Hands‑on experience with container orchestration (Kubernetes) and cloud platforms (AWS).
- Proficiency in building CI/CD pipelines and infrastructure‑as‑code tools.
- Understanding of large language model lifecycle, from training to serving.
- Ability to work independently, communicate effectively with cross‑functional teams, and adapt to fast‑changing AI environments.
Skills
pythonkubernetesdockerawscicdmachine learning