Production Support

P1,C3,STS
Experience 3 to 5 Years of experience in -Design, develop, and deploy GenAI/Agentic AI applications leveraging frameworks such as LangChain, ChromaDB, OpenAI, PyTorch, Streamlit, and other emerging agentic frameworks.
Implement multi-agent systems, orchestration flows, and autonomous task execution using MCP and A2A frameworks.
Perform gap analysis, optimization, and troubleshooting of AI-driven workflows and pipelines.
Build modular, reusable, and scalable AI components integrated into enterprise ecosystems.
Collaborate with product, data, and engineering teams to deliver end-to-end GenAI solutions.
Technical Skills
Secondary Focus: Site Reliability Engineering (SRE)
Provide L2 Support with exposure to Splunk, DataDog, AEM Analytics, AppDynamics, and conduct error/alert log analysis.
Support UI/Infrastructure reliability, monitoring, and incident resolution.
Ensure reliability and performance of AI-powered applications on AWS cloud platforms.
Required Skills & Experience
Proven experience in GenAI/Agentic AI development with a strong grasp of autonomous agents, orchestration, and reasoning frameworks.
Awareness and hands-on exposure to MCP (Model Context Protocol) and A2A (Agent-to-Agent) frameworks.
Strong Python proficiency and expertise with AI/ML frameworks (PyTorch, LangChain, OpenAI APIs, etc.).
Hands-on experience with AWS, especially AWS OpenAI and Cognitive Services.
Familiarity with CI/CD pipelines, modular software design, and testing best practices.
SRE experience in error log analysis, monitoring, and cloud reliability practices