Vetted BERT Professionals

“LLM/RAG engineer who has built and shipped production assistants, including a RAG-based teaching assistant (Marvel AI) using LangChain/LlamaIndex/ChromaDB with OpenAI embeddings and Redis vector search, achieving ~30% accuracy gains and ~35% latency reduction. Also deployed FastAPI services on Google Cloud Run with observability and prompt-level monitoring, and partnered with non-technical ops stakeholders to deliver an internal policy-document RAG assistant.”

“Cross-functional operator/chief-of-staff style leader who took a product from prototype to a live pilot in 3 months, spanning public-sector data normalization, an ML matching engine, a secure API, and KPI/investor demo instrumentation. Strong focus on executive alignment and productivity via Notion-based operating systems plus automated reporting (Python/Power BI), with experience supporting fundraising and go-to-market narratives.”

“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 shipped a production real-time content moderation platform for Zoom/WebEx-style meetings, combining Whisper speech-to-text with fast NLP classifiers and REST APIs to flag hate speech, bias, and HIPAA-related content under strict latency constraints. Demonstrates strong MLOps/infra depth (Airflow, Kubernetes, Terraform/Helm, observability) and a pragmatic approach to reducing false positives via threshold tuning, context validation, and hard-negative data—while partnering closely with compliance and product stakeholders.”

“Built and deployed a production AI invention/patent review platform that compares invention submissions against patent rules to provide instant feedback, reportedly cutting legal team review time by ~80%. Learned Snowflake Cortex LLMs and production deployment (Docker + AWS) on the job, and validated system quality through human-in-the-loop testing with experienced legal stakeholders.”

“Built multiple systems from scratch at DSSD and Aglint, including an NGO sustainability reporting dashboard and a production LLM-powered phone screening agent using Twilio/Retell AI with RAG grounded in PostgreSQL candidate/job data. Strong focus on real-world reliability: guardrails, monitoring, and lightweight eval/regression loops that reduced recruiter score overrides by ~30%. Currently on OPT through May 2026 (plans STEM OPT extension) and committed to relocating to NYC for in-person work; seeking $90k–$120k base with meaningful equity for founding engineer roles.”

“Backend engineer with legal-tech and AI workflow experience: built JurisAI, an end-to-end legal research system using OCR + embeddings + Pinecone vector search to deliver citation-grounded LLM answers with safe failure modes (~90% recall@K). Also led a GW Law metadata migration into Caspio with batch validation and parallel rollout, and has strong FastAPI/GCP production reliability and observability practices.”

“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 owned a production RAG search/Q&A platform at Data Integrity First for a client with a large, hard-to-search document library, deployed on AWS. Drove major adoption gains by adding source attribution (users trusted answers more) and improved system performance with guardrails, logging, and iterative chunking/OCR normalization—cutting fallback rate from ~22% to under 10%.”