Vetted pandas Professionals

“Intern who built and deployed a production LLM-powered contract analysis system for finance teams: Azure Document Intelligence for text/table extraction plus Gemini prompting to surface key terms and risks via an async API and simple UI. Emphasizes reliability in production with fallbacks, guardrails against hallucinations, and operational concerns like latency/cost/versioning, delivering summaries in under 30 seconds instead of hours.”

“Robotics/AI candidate who built an AI-driven landmark location tool during a summer internship at Mobile Drive, combining YOLOv5 object detection with OpenStreetMap-based geolocation to handle dense, cluttered urban environments. Also researched deploying LLM-based agents on constrained hardware using quantization plus LoRA/continuous learning, improving accuracy from ~80% to ~92%, with an emphasis on production logging for reliability.”

“Built a production multimodal LLM-based vendor risk assessment platform that ingests SOC reports and other documents, uses a strict RAG pipeline with grounded evidence (page/paragraph citations), and dramatically reduces analyst review time. Experienced with LangGraph/LangChain/AutoGen for stateful, fault-tolerant agent workflows, and emphasizes reliability (schema validation, guardrails) plus low-latency delivery (~1–2s) through hybrid retrieval, reranking, caching, and model tiering.”

“Built and deployed a production LLM-powered financial risk and compliance platform to reduce manual trade exception handling and speed up insights from regulatory documents. Implemented a LangChain multi-agent workflow with structured/unstructured data integration (Redshift + vector DB) and emphasized hallucination reduction for regulatory safety using Amazon Bedrock. Strong MLOps/orchestration background across Kubernetes, Airflow, Jenkins, and monitoring/testing with MLflow, Evidently AI, and PyTest.”

“At CVS Health, the candidate productionized a RAG-based LLM solution in a regulated healthcare setting, emphasizing reliable data pipelines, LoRA fine-tuning, monitoring, safety guardrails, and A/B testing. They have hands-on experience troubleshooting real-time RAG failures (e.g., chunking/embedding issues) and regularly lead developer-focused demos/workshops while translating technical architecture into business value for stakeholders.”

“Full-stack engineer at an early-stage startup building an agentic AI application for enterprise systems, combining customer-facing Next.js/React UI work (30% faster load times) with backend/workflow orchestration using FastAPI + n8n, Redis, and RabbitMQ. Previously at Deloitte USI, built BDD Selenium/Java automation and managed 200+ defects end-to-end using JIRA/JAMA to support on-time production releases.”

“Full-stack engineer who owned an end-to-end production feature for a Piraeus Bank stock exchange module, spanning React/TypeScript, backend services, and cloud operations with Docker + CI/CD, delivering reported 90% faster API responses and improved uptime. Also built a Smartwound research MVP on AWS, creating a Python image-processing/scoring pipeline to ship despite unclear image-analysis specs.”

“Research Assistant at the University of Houston who built and live-deployed a production RAG system for 1000+ research documents, using hybrid retrieval (dense+BM25+RRF) with cross-encoder reranking and RAGAS-based evaluation; reported 66% MRR, 0.85+ faithfulness, and 68% lower LLM inference costs. Also built a deployed LangGraph multi-agent research system (Researcher/Critic/Writer) with tool integrations (Tavily, arXiv) and dual memory (ChromaDB + Neo4j), plus freelance automation work delivering a WhatsApp chatbot and n8n workflows for a wholesale clothing business.”

“Robotics software engineer focused on multi-robot fleet orchestration in ROS 2, owning the fleet manager and task dispatch layer for pick/drop workflows. Strong in real-world reliability and safety (heartbeats, idempotent tasking, E-stop/localization confidence gates) and in debugging timing/state issues via telemetry alignment and rosbag replay, with experience in simulation, CI/CD, Docker, and Kubernetes-based deployments.”

“Backend engineer who built and evolved a PHI-compliant RAG system (FastAPI + LangChain + embeddings/FAISS) for internal document search and summarization, delivering <400ms p95 latency at ~2,500 daily requests and measurable impact (30% faster investigations, +17% retrieval relevance). Demonstrates strong security and rollout discipline (RBAC/RLS/JWT, redaction/audits, shadow mode, dual writes, canaries) and a focus on reducing hallucination risk via grounded guardrails and confidence-based fallbacks.”

“Senior design robotics engineer on a "Grocery Robot" project selected for the final round of the $10K SICK Challenge, owning ROS2 system design and behavior-tree-based task orchestration across multiple independently developed modules. Also implemented I2C/ESP32 collision avoidance, IK control for a robotic arm, and a Node.js ordering system, with additional research experience using RPLIDAR-based SLAM.”

“Built an end-to-end wafer-data anomaly detection and reporting system at Samsung using PySpark, Random Forest models, SQL, and Grafana to help engineers track faults and take corrective action. Also has strong UX prototyping and validation practices in Figma plus hands-on front-end/full-stack experience (HTML/CSS/TypeScript), including a student project recognized as best design out of 25 teams, and early-stage startup experience pivoting a product based on user interviews into a real-time in-context feedback overlay.”

“Built and deployed a production LLM-powered workflow assistant that automated internal marketing/production business tasks (document summarization, repeated Q&A, status updates). Demonstrates end-to-end applied LLM engineering: modular RAG architecture, hallucination/latency mitigation, automated evals to prevent prompt regressions, and Azure-based orchestration (Functions/Logic Apps) with monitoring and controlled rollouts.”

“Built and deployed a production LLM-powered RAG assistant for healthcare teams (care managers/support) to answer questions from clinical and policy documentation, emphasizing trustworthiness via improved retrieval, reranking, and strict grounding prompts to reduce hallucinations. Also has hands-on orchestration experience with Apache Airflow for end-to-end ETL/ML workflows and applies rigorous testing/metrics (hallucination rate, tool-call accuracy, latency, cost) to ensure reliable AI agent behavior.”

“Early-career engineer from BNP Paribas who drove a large-scale observability modernization—selecting and implementing Prometheus/Grafana for a 2000+ server estate, then productionizing it on Kubernetes via Docker/Jenkins. Known for hands-on demos, strong documentation/templates, and pragmatic troubleshooting (including custom Python metrics) that improved visibility and cut debugging time by ~60%.”

“Built and deployed AcademiQ Ai, a production LLM-based teaching assistant using GPT/BERT with RAG (LangChain + Pinecone) to handle large student notes and generate adaptive explanations/quizzes. Demonstrated measurable retrieval-quality gains (18% precision improvement, 22% less irrelevant context) by tuning similarity thresholds and chunking based on user satisfaction signals. Also orchestrated terabyte-scale, real-time demand forecasting pipelines using Airflow and Kubeflow on GCP with strong monitoring, shadow deployment, and feedback-loop practices.”

“Full-stack engineer who builds TypeScript/React SPAs on Python (Flask/FastAPI) backends and has hands-on experience integrating AI components (Azure OpenAI, LangChain, vector databases) into user workflows. Has built internal AI-enabled dashboards/search tools for analysts and business users, emphasizing typed API contracts, CI/CD-driven quality, and microservices reliability patterns (monitoring, retries, idempotency) at scale.”

“ML/AI engineer with healthcare payer experience (Signal Healthcare, Cigna) who has shipped production fraud/claims prediction systems using Python/TensorFlow and exposed them via FastAPI/Flask microservices integrated with EHR and Salesforce. Emphasizes operational reliability and trust—Airflow-orchestrated pipelines with data quality gates plus SHAP-based interpretability, A/B testing, and drift/debug workflows—backed by reported outcomes of 22% lower false payouts and 17% higher model accuracy.”

“LLM/agentic systems engineer who built a production "Agentic AI Diagnostic Assistant" for network engineers, using a multi-agent Llama 2 + LangChain architecture with RAG over telemetry/incident data in DynamoDB and confidence-based deferrals to reduce hallucinations. Also has strong MLOps/orchestration experience (Airflow, EventBridge, Spark, Docker, SageMaker/ECS) at multi-terabyte/day scale and delivered multilingual NLP analytics (fine-tuned BERT/spaCy) for support operations through hands-on stakeholder workshops.”

“Full-stack engineer with financial services experience (Lincoln Financial) who owned a customer-facing financial portal end-to-end using TypeScript/React and Node/Express. Has hands-on microservices and RabbitMQ event-driven workflows, addressing scale issues like retries/duplicates with idempotency and traceable logging, and built an internal real-time ops/support dashboard to improve monitoring and incident response.”

“Backend-focused engineer with Mastercard experience building and operating high-volume transaction-processing microservices. Has owned customer-facing banking services end-to-end and built an internal on-call analytics tool that centralized logs/metrics with real-time filtering to speed root-cause analysis and reduce incident investigation time.”

“Integration engineer at Epic focused on healthcare interoperability, including complex radiology integrations (orders/results) spanning more than a dozen downstream systems and PACS vendors. Experienced coordinating clinical Radiant teams, interface analysts, and networking teams to scope workflows, route/transform messages via an interface engine, and troubleshoot intermittent production issues using structured isolation and live testing.”

“Built production LLM/RAG platforms for financial services to enable natural-language Q&A over large policy/compliance document sets stored in Snowflake and SharePoint. Strong in MLOps and orchestration (Airflow, ADF, Step Functions, MLflow) and in solving real production issues like stale embeddings and model performance, including an incremental Snowflake Streams sync that cut processing time from hours to minutes.”