AI SRE Engineer

POSITION SUMMARY 

In this role, you will play a key role in designing, developing, and implementing AI-driven tooling and automation to transform and enhance the operations of a critical cloud-based platform. Your primary responsibility will be to identify operational challenges and build intelligent solutions that automate repetitive tasks, accelerate incident detection and resolution, improve observability, and enable more proactive and predictive operations. 

You will work closely with SRE, DevOps, engineering, and platform teams to leverage Generative AI, machine learning, automation frameworks, and operational data to build practical AI-powered solutions for production environments. This will include developing AI agents, intelligent automation workflows, operational assistants, automated alert triage and correlation, root-cause analysis capabilities, and predictive monitoring solutions. 

The role will require a strong understanding of both software engineering and production operations, with a focus on taking AI solutions from concept and experimentation through to reliable, scalable production implementations. Your efforts will help reduce manual operational effort, improve incident response and resolution times, minimize operational risk, and establish a more intelligent, autonomous, and scalable operating model for the platform. 

EXPERIENCE AND REQUIRED SKILL SETS 

Education: Bachelor's degree or master's in computer science, Engineering, Software Engineering or a relevant field 

Experience: Relevant 4+ years of experience in SRE, Production Support, Platform Engineering, DevOps, or a similar technology role, with hands-on experience in Python-based automation and a strong interest or experience in applying AI/Generative AI to production operations. 

Key Responsibilities: 

• Design, develop, and implement AI-powered tooling and automation to improve the reliability, efficiency, and scalability of production operations. 

• Identify repetitive, manual, and time-consuming operational activities and develop intelligent solutions to automate or significantly reduce human intervention. 

• Build and productionize AI/Generative AI solutions for use cases such as incident triage, alert analysis and correlation, log analysis, troubleshooting, root cause analysis, knowledge retrieval, and operational assistance. 

• Develop AI agents, intelligent workflows, and automation frameworks that can assist or execute defined operational activities with appropriate controls and guardrails. 

• Work closely with SRE, DevOps, Development, and Engineering teams to understand operational challenges and translate them into scalable AI and automation use cases. 

• Integrate AI capabilities with existing SRE and production-support workflows, including monitoring, alerting, incident management, knowledge management platforms. 

• Develop solutions that can proactively identify operational anomalies, assist with troubleshooting, recommend remediation actions, and support predictive operations. 

• Measure the effectiveness of AI-driven automation through metrics such as reduction in manual effort, MTTR, alert noise, incident resolution time, and operational toil. 

• Participate in the support of critical production systems and work with SRE/engineering teams during major incidents when AI-driven analysis or automation can accelerate investigation and resolution. 

• Collaborate with stakeholders across time zones and cultures and engage with clients when required to understand operational challenges and demonstrate AI-driven solutions. 

Required Technical Skills 

• Strong Python programming and automation development. 

• Experience with Generative AI, LLMs, AI Agents, and prompt engineering. 

• Knowledge of RAG (Retrieval-Augmented Generation) architectures. 

• Hands-on experience with monitoring and observability platforms. 

• Knowledge of cloud platforms such as AWS, Azure, or GCP. 

• Strong understanding of logging, alerting, troubleshooting, and root-cause analysis. 

Preferred Skills 

• Exposure to LangChain, Semantic Kernel, AutoGen or similar agent frameworks. 

• Machine learning and anomaly-detection experience. 

• Knowledge of vector databases and knowledge-retrieval systems. 

• Familiarity with ServiceNow, Jira, PagerDuty, Splunk, Datadog, Grafana or similar tools. 

Soft Skills 

• Strong problem-solving and analytical mindset. 

• Ability to identify operational inefficiencies and automate them. 

• Effective stakeholder communication. 

• Passion for innovation and applying AI to real-world operational challenges.