Loading profile…
Loading profile…
AI Evaluation and Prompt Engineer
ML Engineer at Bubble 42 evaluating 200+ agentic AI trajectories and diagnosing reasoning and tool-use failures.
PakistanAI Evaluation and Prompt Engineer at Bubble 42
Evaluated 200+ agentic coding trajectories, analyzing tool use and failures using Harbor and opencode. Annotated and validated large datasets, and designed prompts against project rubrics.
Model EvaluationLLM EvaluationHarborOpenCodeDockerLiteLLMPrompt EngineeringData AnnotationQuality Assurance
Built an IT Support Hub with a RoBERTa classifier for automatic ticket routing, and developed AI-based detection of machine problems and production bottlenecks. Also built an AI planning system and a warehouse management system in .NET and SQL Server on Azure.
RoBERTaPython.NETSQL ServerAzureSAPBarcodeMachine LearningData Pipelines
Built automation and AI systems for factory floors, including a RAG assistant for industrial equipment documentation. Extracted live OPC tags from PLCs and built real-time pipelines for dashboards and AI model inputs.
RAGPythonOPC UAPLCAllen BradleySiemensSensor IntegrationData PipelinesAutomation
Pursuing a BS in Computer Science, expected to complete in 2028.
Pursuing a BS in Computer Science, expected to complete in 2028.
Completed a Data Science and AI Certification in 2026.
Completed a Data Science and AI Certification in 2026.