Vetted Workflow Orchestration Professionals

“Built and shipped production LLM systems at Founderbay, including a low-latency voice agent and a graph-based multi-agent research assistant. Strong focus on reliability in real workflows—hybrid SERP + full-site scraping RAG, grounding guardrails, validation checkpoints, and transcript-driven evaluation—plus performance tuning with async FastAPI, Redis caching, and containerization. Also partnered with a non-technical ops lead to automate post-call follow-ups via call summarization, field extraction, and tool-triggered actions.”

“Built and deployed a production LLM-powered internal AI assistant using a RAG pipeline to help teams search internal PDFs/knowledge bases and generate grounded summaries/answers. Demonstrates strong end-to-end ownership (ingestion through APIs) plus production rigor (monitoring/logging/CI-CD, evaluation metrics) and practical optimizations for hallucination, latency, and answer quality (thresholding, fallbacks, caching, async, re-ranking, two-tier model routing).”

“Built and deployed a production LLM-driven document understanding pipeline using LangChain/LangGraph, focusing on reliability via step-by-step prompting, validation checks, and monitoring. Also partnered with non-technical marketing stakeholders at Heartland Community Network to deliver an XGBoost targeting model surfaced in Power BI, improving campaign conversion by 12%.”

“Built and productionized an LLM+RAG lending assistant on AWS to help loan officers quickly answer questions from credit policies and prior decisions, tackling hallucinations with retrieval-only responses and a no-context fallback. Also automated end-to-end ETL and model retraining/deployment using Apache Airflow, and has experience translating clinical stakeholder needs (doctors/care managers) into ML features, metrics, and dashboards.”

“Builder/creator who ships practical AI automations and content workflows: created a no-backend website that uses ChatGPT to generate AI agents/manual workflows, and built an inbound/outbound receptionist using n8n and Retell AI (later migrated to Retell workflows). Also produces an AI-written/produced podcast with 55+ hosts and uses tools like Descript and Sora with make.com for batch content creation and scheduling.”

“LLM engineer who built and deployed an emotionally intelligent AAC communication system using an emotion-aware RAG pipeline (Empathetic Dialogues + GoEmotions) and a PEFT-adapted model. Experienced with LangChain/LangGraph and custom Python orchestration, focusing on reliability (guards, schema validation, fallbacks), latency optimization, and rigorous evaluation (automatic metrics + human-in-the-loop), with a reported 18% user satisfaction improvement.”

“Built and deployed production NLP/LLM systems including a multilingual (5-language) health misinformation detection pipeline with latency optimization (batching/quantization/caching) and explainability (gradient-based attention visualizations). Experienced orchestrating end-to-end AI workflows with Airflow and Prefect, and partnering with customer support ops to deliver an AI agent for ticket summarization and priority classification with clear, measurable acceptance criteria.”

“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%.”

“Built and deployed a production GenAI resume screening and matching system for Florida Atlantic University, focused on improving recruiter efficiency and search relevance. Demonstrates strong RAG engineering (embeddings, query rewriting, metadata filtering, threshold tuning) plus practical reliability work (grounding constraints, fallbacks, and evaluation using real user queries) using Python REST APIs and orchestration frameworks like LangChain and LlamaIndex.”

“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.”

“Backend/platform engineer in fintech/payments (NexaBank/NextBank/Nexon Bank) who has built Kafka-orchestrated Java/Spring Boot microservices around a PostgreSQL double-entry ledger. Led production-critical reliability work preventing duplicate payment postings via idempotency and offset sequencing fixes, and shipped real-time ML fraud scoring (Python model API + Redis caching) with rigorous evaluation/monitoring (Prometheus) and workflow automation for dispute resolution.”

“Software engineer and co-founder with 0-to-1 SaaS experience who built and owned an end-to-end reporting/analytics dashboard on Next.js App Router + TypeScript, including Postgres schema design, aggregation query optimization, and post-launch performance/monitoring. Has delivered measurable React dashboard performance gains (~35% improvement in time-to-insight) and built durable, idempotent job/state-machine workflows using serverless functions and Postgres.”