About this role
Supervised Fine-Tuning (SFT) / Site Reliability Engineer (SRE)
Job
Summary: We are seeking an engineer with experience in AI model fine-tuning and/or Site Reliability Engineering to support AI systems, infrastructure reliability, and production operations.
Key Responsibilities:- Support supervised fine-tuning (SFT) of LLMs, including dataset preparation, data quality validation, training, and model evaluation.- Monitor and maintain the reliability, availability, and performance of AI applications and infrastructure.- Automate deployment, monitoring, and operational tasks using Python and scripting tools.- Troubleshoot production issues, perform root-cause analysis, and improve system stability.- Support cloud infrastructure, CI/CD pipelines, containers, and observability tools.
Required Skills:- Experience with Python, automation, and production systems.- For SFT: familiarity with LLMs, fine-tuning workflows, training datasets, and model evaluation.- For SRE: experience with cloud platforms (AWS/Azure/GCP), Linux, CI/CD, Docker/Kubernetes, monitoring, and incident management.- Strong troubleshooting, analytical, and communication skills.