L3 AI App Support Engineer

Key Responsibilities

• Provide advanced L3 technical support for AI/GenAI applications, including complex debugging, root cause analysis, and code-level resolution.
• Analyse and enhance Python-based AI applications and backend services.
• Troubleshoot and improve RAG pipelines, including retrieval, prompt engineering, orchestration, embeddings, and response quality.
• Work on LLM integrations such as OpenAI API and AWS Bedrock.
• Develop, debug, and enhance applications using LangChain and LangGraph.
• Work with Agentic AI tools and architectures to improve AI application capabilities.
• Support model training, fine-tuning, evaluation, and optimization activities.
• Diagnose application and infrastructure issues across Azure and Kubernetes/AKS environments.
• Work with Azure AI Search/Cognitive Search and Snowflake Cortex Search for enterprise knowledge retrieval.
• Monitor application and model performance using Datadog, Fiddler, and similar observability tools.
• Collaborate with development, platform, and MLOps teams to implement permanent fixes and improve application reliability.
• Participate in release activities, code enhancements, performance improvements, and production deployments.
• Develop and maintain runbooks, troubleshooting guides, technical documentation, and knowledge-base content.
• Identify recurring issues and implement automation or engineering solutions to reduce incidents.
• Contribute to MLOps and LLMOps practices, including deployment, monitoring, model lifecycle, and operationalization.

Required Skills & Qualifications

• 6+ years of experience in software/AI engineering, application support, or a related technical role.
• Strong hands-on experience with Python development and debugging.
• Solid experience with Generative AI, LLMs, RAG, and enterprise AI applications.
• Strong understanding of MLOps and LLMOps concepts.
• Hands-on experience with LangChain and LangGraph.
• Experience with Agentic AI tools/frameworks and AI orchestration.
• Experience with LLM APIs, preferably OpenAI API and AWS Bedrock.
• Strong understanding of RAG architecture, embeddings, vector search, prompt engineering, and retrieval optimization.
• Experience with model training, fine-tuning, evaluation, and performance optimization.
• Hands-on experience with Microsoft Azure and Kubernetes/AKS.
• Experience with Azure AI Search/Cognitive Search and Snowflake Cortex Search.
• Experience with observability tools such as Datadog and Fiddler.
• Strong troubleshooting, debugging, analytical, and problem-solving skills.
• Ability to understand existing codebases, identify defects, and implement code-level solutions and enhancements.
• Ability to work effectively in environments with limited documentation and independently drive technical solutions.