01Key Responsibilities
Design and deploy Gen AI solutions (e.g., chatbots, anomaly detectors) to automate incident triage, root cause analysis, and alerting in production environments.
Integrate AI with existing tools like monitoring systems (e.g., Splunk, Dynatrace, Glass box, Catchpoint), ticketing platforms (e.g., Remedy or ServiceNow), and databases (e.g., Oracle) to improve observability.
Develop custom AI agents or scripts using LLMs (e.g., Claude, Llama, GPT, etc.,) for natural language querying of logs, metrics, and codebases, accelerating MTTR from hours to minutes.
Collaborate with production support teams to identify toil-heavy processes, prototype AI fixes, and measure impact via KPIs like resolution time and ticket volume.
Build and maintain AI pipelines for continuous learning from production incidents, ensuring models improve over time without human retraining.
Ensure AI solutions comply with security, data privacy, and reliability standards in high-stakes financial or enterprise apps.
Train and upskill support teams on AI tools, fostering a culture of AI-driven efficiency.
Preferred Skills:
Proficiency in Gen AI frameworks & Transformers for building RAG (Retrieval-Augmented Generation) systems.
Programming: Python (advanced), with experience in FastAPI, Streamlit for AI prototypes; SQL for database querying (Oracle preferred).
Production support expertise: Incident management, log analysis, MTTR optimization in cloud (AWS/Azure) environment.
AI ops: Model deployment via Docker/Kubernetes, monitoring with Prometheus/Grafana, handling drift and hallucinations.
Data handling: Vector databases (Pinecone, FAISS), prompt engineering for domain-specific tasks like error prediction.
Desired Skills:
MLOps tools: MLflow for CI/CD of AI models.
Observability integration: Custom agents for tools.
Domain knowledge: Global Banking, SRE practices (e.g., SLOs).
Soft skills: Cross-functional communication, agile methodologies, experience converting AI in conservative teams.
Emerging tech: Multimodal AI (e.g., vision for dashboard analysis), fine-tuning open-source models on proprietary incident data
Minimum Qualifications (MustHave) *
58 years total experience, including 35 years of handson GenAI/automation work.
Strong Python skills for scripting, API integration, and automation .
