Vetted Vector Search Professionals

Rubeena Riyas

Screened References

Senior AI Engineer specializing in LLM agents, RAG, and scalable data platforms

7y exp

“ML/data engineer who owned an end-to-end production sales analytics pipeline at 15,000+ user scale, delivering ~50% compute reduction, ~80% faster reporting, and ~$1.2M impact. Also shipped a production RAG-based AI assistant over internal BigQuery/docs with evaluation metrics and safety guardrails, and built shared Python libraries to standardize reliability and accelerate engineering teams.”

“At PwC, built and productionized an agentic RAG enterprise search assistant over 6M internal documents (8M embeddings), deployed across AWS and GCP. Drove major retrieval gains (72%→92% precision via BM25+dense hybrid with RRF and cross-encoder re-ranking), reduced hallucinations 30%, achieved <2s latency at 50–60K queries/month, and cut support tickets 30%—boosting adoption to 2,500 users by adding source-cited answers.”

“Backend/data platform engineer with production experience at Walmart and Molina Healthcare, building Python microservices on AWS (EKS + Lambda) for real-time inventory and recommendation systems. Strong in reliability/observability and incident leadership, plus modernizing legacy healthcare workflows and building resilient AWS Glue/PySpark pipelines with schema evolution and data quality controls.”

“Hands-on LLM practitioner who built a production document-processing pipeline in Python, tackling long-document handling and latency with chunking/batching and a user-driven correction feedback loop. Experienced operationalizing AI workflows with Kubernetes (CronJobs, autoscaling, scheduled data cleaning and weekly retraining) and applying structured testing/evaluation (E2E, LLM-as-judge, HITL) while communicating solutions clearly to non-technical clients using visual diagrams.”

“Worked on onboarding a Middle East logistics client processing thousands of invoices/month, building a production-ready pipeline that routes known vendor PDFs to deterministic regex parsers via Tax ID matching and falls back to LlamaParse for unknown layouts. Added financial consistency validation plus human-in-the-loop review and logging/metrics to continuously reduce LLM usage and improve template coverage.”

“Built and owned an end-to-end agentic RAG chatbot platform for Baptist Health that helped clinicians access policy and clinical documents faster, reducing manual lookup by 80% and delivering about $2M in annual savings. Brings strong healthcare GenAI production experience, including HIPAA-aligned governance, PHI redaction, observability, evaluation, and scalable Python/Kubernetes deployment practices.”

“At Esri, the candidate is building a production LLM-powered WebGIS AI framework that embeds an AI assistant into web maps and routes natural-language requests into ArcGIS JavaScript SDK functions via a LangGraph-orchestrated, multi-agent system. They emphasize production reliability and scale (strict tool calling/JSON, live schema validation, query guardrails) and rigorous evaluation/observability using LangSmith, offline prompt datasets, and latency/tool-call accuracy tracking.”

“Built and deployed a production RAG-based LLM Q&A and summarization platform for internal documents, emphasizing grounded answers with structured prompting and citations to reduce hallucinations. Experienced orchestrating end-to-end LLM workflows with LangChain plus cloud pipelines (Azure ML Pipelines, AWS), and runs iterative evaluation using both metrics (accuracy/hallucination/latency/cost) and real user feedback to drive reliability.”

“Amazon engineer with a blend of backend platform and applied AI experience, spanning Kafka/Spring Boot/Django financial workflows and internal LLM-powered RAG systems for reconciliation investigations. Stands out for owning deployments end-to-end, improving reliability in high-volume transaction processing, and adding practical guardrails like confidence checks and human review to production AI workflows.”