Vetted Retrieval-Augmented Generation (RAG) Professionals

“Built and deployed “ApartmentFinder AI,” a multi-agent system using Google ADK, Gemini, and Google Maps MCP to automate apartment shortlisting and commute-time analysis, cutting a 45–70 minute user workflow down to ~30 seconds. Also has strong delivery/process chops from serving as an SDLC Release Coordinator, managing 52+ releases and reducing SDLC issues by 84%.”

“At Trellis, built and shipped a production multi-agent, authenticated GenAI chatbot for sensitive financial account inquiries (loan/payment lookups), using dynamic model routing to control latency and cost while improving accuracy. Implemented prompt-injection defenses (Meta Prompt Guard), RAG with LangChain, and LLM-as-a-judge evaluation; the system cut manual support call volume by 40%+ and was refined through close collaboration with QA-driven user testing.”

“Built a production Apple-focused LLM Q&A bot that answers user issues using similar past discussion records, including large-scale scraping and cleaning of thousands of forum threads. Used BeautifulSoup + Playwright for static/dynamic extraction, PySpark + NLP for preprocessing, and LangChain RAG with a custom response-likeliness metric to evaluate performance.”

“Full-stack TypeScript/React/Next.js builder who created an end-to-end customer-facing product (AI Job Master) that generates personalized outreach from resumes and job descriptions. Demonstrates strong product + engineering ownership with rapid MVP iteration, instrumentation-driven prioritization, and pragmatic reliability patterns (microservices, queues, correlation IDs, retries) while tackling a key AI challenge: user trust and output consistency.”

“Built and deployed an LLM-to-SQL automation system in a closed/internal environment, using a retriever–reranker–validator architecture on Kubernetes with strong security controls (semantic + rule-based validation and RBAC), achieving 99% uptime and cutting manual query time ~40%. Also worked on genomic sequence classification and semantic search workflows, orchestrating data prep with Airflow, tracking/deploying with MLflow, and optimizing distributed multi-GPU training on a university Kubernetes cluster.”

“At Provenbase, built and shipped a production LLM-powered semantic search and candidate matching platform (RAG with GPT-4/Gemini, multi-agent orchestration, Elasticsearch vector search) to scale sourcing across 10M+ candidate records and 1000+ data sources. Drove sub-second performance, cut LLM spend 30% with routing/caching, and improved recruiting outcomes (+45% sourcing accuracy; +38% visibility of underrepresented talent) through bias-aware ranking and tight collaboration with recruiting stakeholders.”

“Built and productionized a RAG-based semantic search system for video-derived data, focusing on measurable success metrics (p95 latency, reliability, cost/request) and strong observability (prompt versions, retrieved docs, tool calls, token usage). Experienced in diagnosing real-time issues in LLM/agentic workflows and in supporting go-to-market efforts through tailored technical demos, rapid POCs, and post-close onboarding.”

“Built and productionized a domain-specific LLM-powered RAG knowledge assistant at JerseyStem for answering questions over large internal document corpora, owning the full stack from FAISS retrieval and LoRA/QLoRA fine-tuning to AWS autoscaling GPU deployment. Drove measurable gains (28% accuracy lift, 25% latency reduction) and improved reliability through hybrid retrieval, grounded decoding, preference-model reranking, and Airflow-orchestrated pipelines (35% faster runtime), while partnering closely with non-technical stakeholders to define success metrics and ensure adoption.”

“Junior web developer turned applied AI builder who has shipped both user-facing web UX improvements (Vue.js + Drupal/Twig) and production LLM systems. Built a Google Cloud-hosted Llama/Ollama RAG customer-service chatbot with citation-based guardrails and a metrics-driven eval loop, and also delivered a large-scale Python pipeline analyzing 14M Amazon consumer reviews for flavor-trend detection.”