Vetted Large Language Models Professionals

“Currently working in CoRAL Lab, built and deployed IntegrityShield—a document-layer PDF watermarking system that keeps assessments visually identical while disrupting LLM-based solving; validated in a real classroom where it helped catch 12 AI-cheating cases. Also built MALDOC, a modular red-teaming platform for document-processing AI agents using LangGraph to run reproducible, deterministic adversarial trials across OCR/text/vision routes.”

“ML/LLM engineer who has deployed a production LLM-powered assistant for intent classification and query routing (order recommendation/support deflection), combining BERT fine-tuning with an embedding-based retrieval layer and optimizing for low-latency inference. Experienced with end-to-end reliability practices—Airflow-orchestrated ETL, data validation/alerting, MLflow experiment tracking, and iterative improvements driven by user feedback and monitoring.”

“ML/LLM practitioner who has deployed a production RAG-based trouble-call identifier using multiple datasets (device, network, past complaints). Experienced in end-to-end MLOps (FastAPI + Docker + Kubernetes with HPA) and in evaluating/monitoring LLM behavior to reduce hallucinations, with additional applied work in forecasting/anomaly detection and churn prediction for retention campaigns.”

“Built and deployed a production RAG-based internal knowledge assistant that let analysts query company documents in natural language, using LangChain/LangGraph with Pinecone and a FastAPI service for integration. Emphasizes reliability in production through hallucination mitigation (retrieval tuning + prompt guardrails) and measurable evaluation/monitoring (accuracy, latency, task completion, hallucination rate), iterating based on user feedback.”

“Entrepreneur building an applied-AI tool for geological resource exploration (critical minerals, oil & gas) that overlays proprietary and public data from reports/logs/maps to generate evidence-based greenfield profiling insights. Has spent ~2 years on industry research, built a POC, validated demand with purchasing signals, and developed partnerships/network including USGS, DARPA, and ESRI.”

“At KPMG, built and productionized a secure RAG-based LLM assistant that lets business and risk stakeholders query data warehouses in natural language, reducing dependence on data engineers for ad-hoc analysis. Demonstrates strong production rigor (Airflow orchestration, CI/CD, containerization), retrieval/embedding tuning (rechunking, semantic abstraction for structured data), and reliability controls (confidence thresholds, refusal behavior, monitoring and canary evals).”

“Built and deployed a production agentic LLM knowledge assistant that answers complex questions over internal documents, APIs, and databases using a RAG architecture (FAISS/Pinecone) and LangChain/LangGraph orchestration. Emphasizes production-grade reliability and hallucination control through grounding, confidence thresholds, validation, retries/fallbacks, and full observability (logging/metrics/traces) with continuous evaluation and feedback loops.”

“ML/GenAI engineer with production experience building an LLM-powered governance layer that summarizes verified drift/performance signals into validation reports and release notes, designed for regulated environments with de-identification and non-blocking fallbacks. Strong Airflow-based orchestration background across healthcare and finance, integrating Databricks/Spark and MLflow for scalable retraining/monitoring. Demonstrated ability to partner with non-technical healthcare operations teams to deliver actionable risk-scoring outputs via dashboards and automated reporting.”

“Robotics software developer building an ESP32/FreeRTOS wheel-encoder driver for a differential-drive robot with PID velocity control and ROS2 odometry publishing. Has implemented vision-based human tracking (DepthAI) and an obstacle map + EKF sensor fusion using IMU and LiDAR, with a simulation-first debugging workflow (Gazebo, Foxglove) and Dockerized environments; plans to extend to Nav2 + SLAM Toolbox for building-scale mapping.”

“Built and deployed a production LLM-powered biomedical knowledge extraction pipeline that processed millions of papers to identify tools/techniques and produce a unified knowledge graph via active learning NER (Prodigy + spaCy transformers) and entity linking (Bio-tools/Wikidata). Addressed hard NLP engineering challenges like WordPiece span-offset alignment and scaled inference over ~1.5M documents using batching/caching, containerized services, async workers, and orchestration with Prefect/Airflow.”

“Built and deployed LLM-powered agentic systems including a multi-agent travel planning assistant using LangChain, RAG (FAISS), real-time APIs, and a supervisor agent to manage coordination and reduce hallucinations. Also developed a Text-to-SQL system with schema-aware validation guardrails, and collaborated with drilling domain experts at CNPC USA to build an ML model predicting rate of penetration (ROP).”

“Maintained and improved a set of JavaScript packages at JPMorgan, including a major refactor of an event-emission layer used in LLM streaming that delivered ~20% runtime speedup with no API changes. Known for a measurement-driven performance approach (profiling + simplification + validation), strong backward-compatibility discipline, and documentation that accelerates internal adoption and reduces support questions.”

“New grad SDE (AI/ML) who built and deployed an LLM-based chatbot framework used across technology, military, and banking contexts, focusing on model selection tradeoffs (latency vs accuracy) through prototyping and benchmarking. Also built a multi-agent "eaterybot" using PyAutoGen/AutoGen with a manager agent orchestrating specialized agents, and emphasizes rigorous testing with adversarial/edge-case datasets and hallucination checks.”

“Engineering/technology leader who spearheaded an ultra low-latency AI-CDN SaaS platform on a multi-cloud stack (AWS/Azure/Alicloud), helping transform ARHT from a boutique provider into a global SaaS solution. Built distributed engineering and follow-the-sun support teams and helped secure major enterprise clients (TD Bank, Gucci, NATO, EY) while also leading board communications and raising $6M for a public-listed company.”

“Backend/data platform engineer who led a major redesign of a hybrid streaming+batch analytics platform processing 10+ TB/day (Airflow/Hive/BigQuery) with strong data-quality automation. Also built a production RAG PDF assistant with concrete mitigations for hallucinations and prompt injection (re-ranking, grounding, verifier step) and has deep experience executing low-risk migrations (dual-write, blue-green, rapid rollback) and implementing JWT-based row-level security.”

“Built and deployed a compliance-sensitive LLM pipeline that extracts rebate logic from hospital–supplier medical contracts, using multi-layer redaction (regex/NER/dictionary), schema-validated structured outputs, and secure placeholder reinsertion. Hosted models on Amazon Bedrock to avoid retraining on sensitive data and improved both accuracy and cost by splitting the workflow into a lightweight section classifier plus a fine-tuned extraction model, orchestrated with LangChain and evaluated via layered, test-driven agent assessments.”

“Built a production multimodal LLM system (Gemini on GCP) to automate behavioral coding of family-involved science experiment videos, including preprocessing for inconsistent lighting/audio and LangGraph-orchestrated parallel workflows. Also developed rubric-based AI grading workflows and partnered closely with non-technical education stakeholders through explainability-focused walkthroughs and manual-vs-AI evaluation alignment.”

“Built and owned a production-scale AI-driven software release/version intelligence platform orchestrated via GitHub Actions that tracks 1000+ upstream repositories and automatically generates SLA-bound JIRA upgrade tickets for hardened container images. Replaced brittle regex/PEP440 parsing with an LLM-based semantic filtering layer plus deterministic validation to handle noisy/inconsistent GitHub tags at scale, with monitoring for coverage, latency, and correctness validated against upstream ground truth.”

“Built and deployed a production-style vision-language pipeline that generates structured medical reports from chest X-rays using BioViLT embeddings, an image-text alignment module, and BiGPT fine-tuned with LoRA, delivered via Streamlit and hosted on AWS EC2. Also collaborating experience presenting EDA findings, feature importance, and model performance to Ford managers while working with vehicle parts data at Bimcon.”

“Master’s-in-Data-Science candidate (UHV) with 4+ years in AI engineering building production LLM and multimodal systems. Designed an LLM-powered workflow automation platform using RAG over vector stores with guardrails (schema/output validation, fallbacks) and a rigorous evaluation/monitoring framework including drift tracking and shadow deployments. Experienced orchestrating large-scale vision-language pipelines with Airflow and Kubernetes (OCR, distributed training) and partnering with non-technical ops stakeholders to cut cycle time and reduce errors.”

“Built a production, agentic multi-agent pharmaceutical intelligence system for US oncology (breast cancer) conference/news intelligence, automating MSL-style information gathering and summarization for pharma and healthcare stakeholders. Uses CrewAI + LangChain orchestration, custom scraping across ~15 pharma newsrooms, and a grounding-score evaluation approach (sentence transformers/cosine similarity) to mitigate hallucinations.”

“Designed and deployed an enterprise LLM-powered clinical/pharmacy policy knowledge assistant at CVS Health, replacing manual searches across PDFs/Word/SharePoint with a HIPAA-compliant RAG system. Built end-to-end ingestion and orchestration (Airflow + Azure ML/Data Lake + vector index) with PHI masking, versioned re-embedding, and production monitoring (Prometheus/Grafana), and partnered closely with clinicians/compliance to ensure policy-grounded, auditable answers.”

“AI/LLM engineer with recent production experience at UnitedHealth Group building an end-to-end RAG system over structured EMR data and unstructured clinical notes, including evidence retrieval, GPT/LLaMA-based reasoning, and a validation layer for reliability. Strong in orchestration (Kubeflow/Airflow/MLflow), prompt engineering for noisy healthcare text, and rigorous evaluation/monitoring with gold-standard benchmarking, plus close collaboration with clinical operations stakeholders.”