Vetted Retrieval-Augmented Generation Professionals

Nikhitha santhoshi Maroju

Screened

Mid-level Full-Stack Software Engineer specializing in Java/Spring microservices on AWS

Redwood, CA4y exp

“Built and shipped a production LLM-powered fraud investigation agent using RAG to generate transaction explanations and draft analyst reports. Emphasizes production robustness (fallbacks, strict structured outputs, async orchestration, monitoring/evals) and reports measurable impact: ~12% precision lift and ~80 high-priority alerts per week with reduced manual effort.”

Michael Yeung

Screened

Mid-level Software Engineer specializing in FinTech trading platforms

San Francisco, CA4y exp

“Built and deployed internal trading tools at Wells Fargo that reduced manual production-support dependency for trader configuration workflows. Brings hands-on experience in financial systems, data quality, and production incident resolution, including building 400+ SQL validation rules and designing an internal RAG assistant for engineering documentation.”

“ML/AI engineer focused on taking LLM products from experiment to production, with hands-on ownership of a RAG-based customer support system that improved response quality by 35% and cut latency by 30%. Stands out for combining product impact with production rigor across retrieval tuning, safety guardrails, monitoring, and reusable Python/FastAPI services that accelerated adoption across teams.”

Paavani Karuturi

Screened

Junior Backend and ML Engineer specializing in distributed systems and LLM infrastructure

San Jose, CA2y exp

“Backend engineer with strong ownership across authentication, API infrastructure, and AI-powered document workflows. They built and operated a production auth microservice supporting 10,000+ users with measurable latency and security improvements, and also shipped hackathon and applied-AI systems including legal document and medical document retrieval/Q&A products.”

Sriram Degala

Screened

Senior AI/ML Engineer specializing in healthcare and finance AI

Dallas, TX4y exp

“Built production-grade medical AI systems at MD Anderson, including an end-to-end RAG chatbot used by clinical researchers for real-time drug interaction and trial literature queries. Stands out for combining healthcare domain knowledge with strong MLOps, evaluation, and safety practices, and for delivering measurable gains in latency, retrieval precision, and team adoption.”

Michael Boaz

Screened

Senior Software Developer specializing in cloud-native and event-driven architecture

Atlanta, GA24y exp

“Built and shipped production LLM/agent systems on AWS for internal developer support and IT observability use cases, including a Claude-based support tool grounded in internal documentation and a cost-optimized ServiceNow integration. Stands out for combining agent design, cloud architecture, CI/CD, chaos testing, and observability to make non-deterministic systems reliable and maintainable in production.”

“Full-stack engineer who built BrewAI, a cloud-native AI resume optimization platform on GCP using React, TypeScript, LangChain, and Gemini, with scalable async job processing and LLM safety guardrails. The product gained real-world traction when an undergraduate college in India asked students to use it for internship resume drafting, and the candidate also has team lead experience shipping an early-stage ERP system.”

Chuangyu Xu

Screened

Entry-Level Software Engineer specializing in Java backend and distributed systems

New York, NY

“Built and shipped a production AI mock-interview platform where an LLM “interviewer” generates role-specific questions, runs multi-turn follow-ups, and outputs structured scoring/feedback using RAG. Demonstrates strong production-readiness practices (Prometheus/Grafana monitoring, retries/timeouts, fallback models/templates, schema validation, replay-based debugging) and achieved 99%+ availability with ~40% higher session completion. Also has experience integrating agents with messy SAP/ERP-style data sources using a data middleware layer, cleaning/validation, and idempotent write safeguards.”

“Applied NLP/ML engineer with experience at KeyBank and Novartis building production document intelligence and entity-resolution systems in finance and healthcare. Has delivered end-to-end pipelines (Airflow + AWS) using transformers (DistilBERT/Sentence-BERT), vector search (FAISS/Milvus/Pinecone), and human-in-the-loop labeling to achieve measurable gains (40%+ faster queries; up to 88% F1 and 93% precision/90% recall in entity linking).”

“GenAI/RAG engineer who has deployed a production policy/regulatory search assistant for a financial client using LangChain + Vertex AI, FastAPI, Docker/Kubernetes, and Airflow-orchestrated data pipelines. Demonstrated measurable impact with 50–60% latency reduction and 70% fewer pipeline failures, plus KPI-driven grounding evaluation (90%+ target) and strong cross-functional collaboration with compliance/business teams.”

“Built and owned an end-to-end RAG-based AI support platform at Mechanize (FastAPI/LangChain/Pinecone/React) with rigorous evals and guardrails, driving 45% fewer support tickets and ~$280K annual savings. Also led a high-risk legacy modernization at Argo AI, incrementally extracting a monolithic Django backend using Strangler Fig + feature flags while supporting 10K+ concurrent users.”