Vetted Research Assistants in New Jersey

“Built and productionized an LLM-driven document verification workflow for a construction firm’s submittals process, moving from a Vercel/Next.js prototype to a FastAPI + LangChain/LangGraph backend with background workers and multi-server deployment. Uses LLM tools (e.g., OpenAI Codex/Cloud Code) for rapid development and log-driven root cause analysis, and partners with customer teams on evaluation metrics and iterative improvements.”

“ML/NLP engineer focused on large-scale data linking for e-commerce-style catalogs and customer records, combining transformer embeddings (BERT/Sentence-BERT), NER, and FAISS-based vector search. Has delivered measurable lifts (e.g., +30% matching accuracy, Precision@10 62%→84%) and built production-grade, scalable pipelines in Airflow/PySpark with strong data quality and schema-drift handling.”

“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.”

“Built and deployed production LLM applications including a natural-language-to-read-only-SQL system focused on ambiguity handling and query safety (schema whitelisting, intent validation, confidence checks, deterministic execution). Experienced with LangChain-based, modular agent orchestration and RAG document QA for large PDFs, with a metrics-driven testing/evaluation approach and cross-functional delivery with marketing on an AI content recommendation/search tool.”

“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.”