Vetted Workflow Orchestration Professionals

“Built and productionized a real-time social-media sentiment analysis system used by a marketing team to monitor brand/campaign performance. Experienced in orchestrating LLM workflows with LangChain (validation → prompting → parsing → post-processing), plus monitoring, retraining, and RAG-style retrieval using embeddings/vector stores to keep outputs reliable over time.”

“Full-stack engineer from Larix Technologies who led a Next.js migration feature: an internal real-time workflow status dashboard built with App Router/TypeScript using server components for initial render and client polling for live updates. Demonstrates strong post-launch ownership—monitoring latency/error rates, adding caching and payload reductions, and optimizing Postgres queries/indexes—plus experience building durable RabbitMQ-based message routing workflows with idempotency, retries, and dead-letter queues.”

“Data/NLP practitioner who builds production-oriented pipelines for unstructured text: entity extraction, topic modeling (LDA/BERTopic), and semantic search using Sentence-BERT embeddings with FAISS. Emphasizes rigorous evaluation (coherence/silhouette + manual review), entity resolution with validation, and scalable workflow orchestration using Airflow/Prefect with Spark/Dask.”

“Solo builder of OGym, shipping production AI features for gyms that turn member behavior/health data (workouts, attendance, nutrition, payments, device metrics) into prioritized, actionable owner and member insights. Designed and implemented FastAPI backends, PostgreSQL-based RAG workflows, guardrails (RBAC/validation/rate limiting), and real-user evaluation loops, with a strong focus on latency/cost optimization and reliable data pipelines.”

“Built and deployed a production RAG-based internal document Q&A system using LangChain, vector search, and a dockerized FastAPI LLM service. Focused on reliability by systematically reducing hallucinations and improving retrieval through prompt grounding/abstention strategies, chunking and top-k tuning, and iterative evaluation with logged metrics and manual validation.”

“AI/LLM engineer who has shipped production RAG and agentic systems end-to-end (LangChain/FAISS, OpenAI+Gemini, FastAPI, Docker, Streamlit), focusing on retrieval quality and low-latency performance. Also partnered with a non-technical PM at deepNow to deliver a forecasting + summarization pipeline for daily market insights with iterative prototyping and a simple UI.”

“Built an end-to-end car maintenance application from design through deployment using TypeScript/React with a Node.js + Firebase backend, including OBD integration. Uses mock servers and a layered frontend architecture (UI/state/services separation) to iterate quickly on UX without being blocked by backend or hardware dependencies.”

“Data Science honors graduate (Maryville University) who has built Python/SQL backends and a capstone website handling sensitive user data. Emphasizes secure data handling (password encryption, secure database updates) and uses Git/GitHub Pages with CI/CD-style practices for managing and deploying changes.”

“Built and deployed a production bilingual (Bengali/English) AI virtual assistant that replaced IVR for telecom customer service at massive scale (~15M users), integrating ASR/TTS, Rasa dialogue management, and custom NLP. Overcame low-resource Bengali data and noisy call-center audio with synthetic data augmentation and transformer fine-tuning, achieving significant production gains including ~50% reduction in support calls.”

“Built and shipped an AI-powered journaling app feature that analyzes user text for emotions in real time, owning everything from React/TypeScript UX (dynamic theming + Framer Motion) to a FastAPI backend integrating Hugging Face. Has hands-on production experience deploying Dockerized services on AWS (EC2/RDS/S3/CloudWatch) with GitHub Actions CI/CD, and resolved a real latency/scaling incident by converting blocking external API calls to async with retries/timeouts.”