Vetted Model Evaluation Professionals

“AI/back-end engineer at Canon who helped build and operate an internal production LLM platform that acts as a secure middle layer between users and models, defending against jailbreaks/prompt injection while enabling RAG, memory, and grounded responses over company data. Experienced with LangChain/LangGraph orchestration, vector DB retrieval, and reliability practices (testing, monitoring, adversarial prompts) to run high-throughput, low-latency AI workflows in production.”

“Built and deployed LLM-powered features for a startup organizational management application, focusing on real-world deployment constraints like latency and cost. Implemented RAG with FAISS and improved retrieval quality by switching embedding models (OpenAI/Hugging Face) and fine-tuning embeddings on medical corpora for a medical-report UI feature. Uses LangChain and LangGraph to orchestrate multi-node LLM API workflows and evaluates systems with metrics like latency, cost per request, and error taxonomy.”

“Built and deployed a production LLM-powered text-to-SQL/document intelligence chatbot on AWS that lets non-technical business users query complex enterprise databases in plain English. Demonstrates deep practical expertise in schema-aware prompting, embeddings-based schema retrieval, SQL safety/validation guardrails, and rigorous offline/online evaluation with human-in-the-loop approvals for risky queries.”

“Built a production-grade, semi-automated document recognition and classification system for large volumes of scanned PDFs, starting from little/no labeled data and handling highly variable scan quality. Deployed on AWS using SageMaker + Docker and orchestrated on EKS with a microservices design that scales CPU-heavy OCR separately from GPU inference, with strong reliability controls (validation, fallbacks, retries, readiness probes).”

“Built AI-EDU, an AI/LLM-powered learning platform created for a Technology Entrepreneurship class that predicts student engagement and generates personalized learning insights. Emphasizes strong data preprocessing/feature engineering on noisy student data, and has experience operationalizing workflows with basic Airflow/Prefect plus reliability practices (edge-case testing, metrics, logging, guardrails) and stakeholder-friendly dashboards/summaries.”

“Data/ML practitioner who has built a production RAG-based knowledge assistant integrated into Microsoft 365/internal dashboards to help employees query internal documents in plain English. Experienced orchestrating and hardening ETL pipelines with Airflow and Azure Data Factory (validation, retries, monitoring) and running end-to-end model evaluation and production performance tracking via Power BI.”

“Data scientist/researcher who has built two multimodal LLM systems: an AI-assisted medical triage pipeline using GPT-4o vision + RAG with confidence-scored red/yellow/green outputs, and a master’s project on multimodal cyberthreat detection combining multiple models and using TinyLlama to generate human-readable risk reports. Also partnered with business analysts at Sanvar Technologies to deliver a churn prediction pipeline and Tableau dashboard for decision-making.”

“Backend-focused engineer who built an academic AI voice assistant with a Python microservice-style backend (speech recognition, spaCy-based NLP, and Kafka-driven automation) optimized to sub-500ms latency. Also has Sodexo internship experience deploying containerized services across Kubernetes/AWS ECS/Azure using ArgoCD GitOps, including solving config drift and secret-management challenges and supporting cloud-to-on-prem migrations with blue-green rollouts.”

“Backend/AI engineer who has built production LLM orchestration and agentic workflow systems in Python/FastAPI on Kubernetes across AWS/Azure. Demonstrated strong reliability engineering by debugging a real-world memory retention issue that caused latency spikes/timeouts, and strong data/performance chops with a PostgreSQL optimization that cut query latency from ~1.2s to ~15ms. Targets roles building scalable, guardrailed AI-driven workflow automation with robust observability and human-in-the-loop controls.”

“Data science professional who has built a production RAG-based LLM question-answering system ("Flash Query") to deliver fast, accurate answers over large document collections, focusing on retrieval quality and grounded responses. Also collaborates with non-technical retail/jewelry stakeholders to turn business questions into predictive models and dashboards for decision-making.”

“Full-stack engineer who has shipped and operated generative-AI chat/QA features end-to-end, including a RAG-based pipeline with guardrails and cost/latency monitoring in production. Experienced with React/TypeScript + Node/Postgres architectures, Dockerized deployments to AWS (EC2) via GitHub Actions CI/CD, and building reliable ingestion/ETL systems with idempotency, backfills, and reconciliation.”

“Currently at ProShare and reports building an AI/LLM-powered system deployed to production, aimed at helping with status-related difficulties and reducing misunderstandings across transactions. Also cites prior collaboration at Porsche with marketing teams, focusing on translating marketing goals into technical requirements and communicating solutions clearly to non-technical stakeholders.”

“Early-career AI/LLM builder who created and deployed a multi-agent news analysis agent (Patrakarita) using CrewAI, coordinating researcher/analyst roles to turn noisy article URLs into structured, prioritized outputs (claims, tone, verification questions, opposing views). Strong focus on orchestration debugging and reliability evaluation, including measuring hallucination/redundancy and improving reasoning by refactoring pipeline sequencing.”

“Built and deployed a production RAG-based LLM assistant that answers day-to-day operational questions from internal PDFs/SOPs, with strong emphasis on data consistency (metadata versioning, confidence thresholds, conflict handling) and low-latency retrieval at scale. Experienced designing and orchestrating multi-agent LLM workflows (retrieval/validation/generation) and pipeline orchestration for ingestion/embedding/vector-store updates, plus iterative delivery with non-technical operations/business stakeholders.”

“LLM workflow builder who has deployed a personalized GPT experience (including Delphi AI-based knowledge ingestion) and built a LangChain/LangGraph job-aggregation pipeline that ingests, normalizes/dedupes, filters, then uses an LLM to rank and summarize matches. Emphasizes production reliability with structured outputs, retries/fallbacks, metric-driven evaluation, logging/prompt versioning, and A/B testing, and collaborates with non-technical stakeholders through demo-driven iteration.”

“Built and deployed a production generative-AI copilot at Tungsten that automates invoice/form extraction template creation, reducing weeks of manual model-building work. Combines fine-tuned LLMs (PyTorch/HuggingFace) with OpenCV layout grounding to reduce hallucinations, and runs an end-to-end Kubeflow-based MLOps pipeline with drift monitoring, canary releases, and automated retraining.”

“LLM engineer who has deployed a production RAG system (LangChain/FAISS/FastAPI) for enterprise semantic search, tackling real-world latency by LoRA/PEFT fine-tuning and grounding outputs with retrieval. Brings strong MLOps (Docker, AWS EKS, CI/CD, MLflow) plus stakeholder-facing explainability experience using SHAP to align ML-driven financial guidance with non-technical domain experts.”