Vetted NumPy Professionals

“Built and deployed a production healthcare medical review agent that automates call-transcript summarization and medication reconciliation using a hybrid deterministic + LangGraph-orchestrated LLM workflow. Demonstrates strong reliability engineering (guardrails, schema validation, confidence thresholds, golden/adversarial eval, Langfuse monitoring) in a regulated environment, delivering 60% lower latency and 70%+ efficiency gains while partnering closely with care managers and operations.”

“Full-stack engineer (~4 years) who has owned and shipped customer-facing SaaS onboarding and a role-based real-time analytics dashboard using TypeScript/React with a modular backend. Experienced in microservices with RabbitMQ and strong observability practices (correlation IDs, structured logging, queue metrics), and built an internal deployment tracker integrated with CI/CD that replaced manual spreadsheet/Slack processes.”

“Python/ML engineer with strong DevOps depth: built an end-to-end regime-aware stock prediction system (custom fine-tuned FinBERT sentiment + technical/macro features) delivering a 12% accuracy lift. Also implemented Kubernetes/Helm + Jenkins/GitHub Actions pipelines (including GitOps-style workflows for multi-cloud Hyperledger Besu) and improved deployment speed/stability by ~50% while addressing race conditions and image drift.”

“AI/LLM engineer at Capital One who deployed a production RAG-powered fraud analysis and document intelligence platform using LangChain, OpenAI, Pinecone, Kafka, and AWS. Focused on reliability in real-time investigations via hybrid retrieval, schema-validated outputs, and LLM verification loops, reporting review-time reduction from hours to minutes and ~99% fraud detection precision.”

“Built and productionized a RAG-based analytics Q&A assistant for a financial analytics team, enabling natural-language querying across 200+ datasets (SQL tables, PDFs, compliance docs, wikis) and cutting turnaround time by 60%. Deep experience delivering regulated, audit-ready LLM systems on Azure (Azure OpenAI + LangChain) with strict grounding/citations, hybrid retrieval, and AKS-based low-latency deployment, plus strong collaboration with compliance analysts and auditors via iterative Gradio demos.”

“Backend/ML-systems engineer with experience (including Amazon) building real-time face recognition services using PyTorch (MTCNN/FaceNet) and AWS (SQS/S3/Lambda/EC2) with a focus on low latency, burst handling, and cost control. Also led a revenue-critical legacy pricing workflow migration to a serverless event-driven architecture using strangler-pattern rollout, simulation-based validation, and strong security practices (JWT/RBAC/RLS).”

“Engineering player-coach who recently shipped an agent-based workflow to extract key info from unstructured web data (browser agents + CDP) and populate daily digests/calendars, owning architecture through testing. Also built a Flask-based LLM evaluation and regression testing system using G-Eval/Confident AI dashboards, and applies a rigorous, research-driven approach to selecting third-party tools with stakeholder buy-in; has healthcare ops/onboarding workflow experience at Vivio Health.”

“Built and productionized an LLM-powered clinical assistant at a healthcare startup, re-architecting a prototype into a robust RAG system on AWS with guardrails, citations, monitoring, and automated tests for clinical reliability. Works closely with clinicians to convert workflow feedback into evaluation criteria and iterative system improvements, and has hands-on experience debugging agentic systems in real time (including during live client demos).”

“Backend engineer with hands-on experience building Flask REST APIs (auth, CRUD, S3 media uploads) and driving measurable Postgres/SQLAlchemy performance gains (p95 reduced to 200–400ms by eliminating N+1s and switching to keyset pagination). Implemented multi-tenant isolation with strict tenant scoping plus Postgres RLS, and built an OpenAI-powered quiz generation pipeline using queued workers, structured JSON outputs, and Celery/Redis optimizations to stabilize high-throughput workloads.”

“CMU candidate with hands-on experience taking LLM concepts from research prototypes toward production-ready designs (structured outputs, guardrails, failure-scenario evaluation). Also partnered with sales/customer teams at Mazecare to drive adoption with Dontia Alliance (largest dental clinic chain in Singapore) and engaged Singapore government stakeholders, bridging clinical workflow needs with IT security/integration concerns.”

“Built and deployed a retail customer review intelligence platform by fine-tuning BERT for sentiment/topic extraction and pairing it with a recommendation component. Demonstrates strong production ML rigor (error analysis, relabeling/active sampling, thresholding/guardrails, OOD checks) and AWS-based orchestration at scale (Lambda + SageMaker with batching and concurrency controls), plus proven ability to align non-technical stakeholders on measurable outcomes.”

“Built and deployed a production multi-agent RAG system at JPMorgan Chase to automate regulated credit analysis and compliance clause discovery across large internal policy/document libraries. Implemented LangGraph-based supervisor orchestration with structured state management (Azure OpenAI) to support long-running, resumable workflows, plus hybrid retrieval + re-ranking and guardrails for reliability. Strong at evaluation/observability (trace logging, LLM-judge, HITL) and at communicating results to non-technical stakeholders via Power BI embeds and Streamlit prototypes.”

“Built and deployed an on-prem, HIPAA-compliant LLM pipeline for oncology-focused clinical note generation and decision support, emphasizing grounded differential diagnosis and explainable reasoning via RAG to reduce hallucinations. Also created a LangGraph-based multi-agent academic paper search system integrating Tavily, arXiv, and Semantic Scholar with an orchestrator that routes tasks to specialized sub-agents.”

“Built and shipped a production LLM-powered multi-agent RAG system to automate complex internal support workflows, integrating tool execution (SQL/APIs) with validation guardrails to reduce hallucinations. Optimized for real-world latency and cost via model routing, caching, and async parallel tool calls, and enforced reliability with CI-gated golden test sets derived from anonymized production queries.”

“Cloud infrastructure/product engineer with end-to-end ownership of cloud-native storage/observability products, including taking an internal CMS to Google Cloud Marketplace and scaling to ~40,000 deployments. Strong in Kubernetes-based platforms (Operators, microservices, RabbitMQ) and performance/scalability work (e.g., 200% cluster capacity increase) plus internal tooling that materially improved SRE/QA debugging and release velocity.”

“Sourcing/procurement-focused candidate who owned vendor selection and risk planning for an IoT pressure/temperature gauge prototype, partnering with a procurement expert on negotiations. Demonstrates strong operations/process mindset by fixing a sales-to-production handover bottleneck with a simple checklist and managing milestones via master trackers and RACI.”

“Built a production LLM-powered RAG agent for healthcare/insurance operations that retrieves and summarizes patient medical documents with grounded citations, scaling to ~4.5M records. Addressed medical shorthand and terminology by fine-tuning ~120 lightweight DistilBERT models by specialty and validating entities against SNOMED/RxNorm, while using SHAP/LIME and human-in-the-loop review to make decisions explainable to stakeholders.”

“Data/analytics professional with experience across manufacturing and enterprise environments (Wisconsin School of Business project with CNH Industrial; roles/projects at Ascensia Technologies, S&C, and Adobe). Has hands-on work combining warranty/lifecycle tables with technician free-text notes using TF-IDF + tree models (XGBoost/Random Forest), and deep experience in entity resolution/reconciliation across mismatched financial systems using Python/SQL and fuzzy matching, with production-grade pipeline practices in Azure Data Factory/Databricks.”

“ML/NLP practitioner working across healthcare and business/finance use cases: currently fine-tuning a domain-specific Llama 3.1 model for safe reasoning over EHRs/clinical notes using RAG + RL/DPO and RAGAS-based evaluation. Has built UMLS-driven entity normalization pipelines with quantified quality gains and developed embedding/vector-DB systems (FAISS) for semantic matching and forecasting/recommendation applications at Aurora AI and Banxico.”

“Robotics software engineer with hands-on experience building a dual-arm (Kawasaki duAro) Cranfield assembly task-planning and motion-planning stack in ROS/MoveIt, using PDDL + behavior trees and OMPL for collision-free execution. Improved tight-tolerance insertions by integrating RGB-D visual servoing into the task planner loop, and also built an LLM-driven navigation pipeline with ORBSLAM3 for natural-language command parsing and real-time replanning.”

“Full-stack engineer building real-time internal banking operations dashboards (Java/Spring Boot microservices + React/TypeScript) with Kafka-based streaming and post-launch performance optimizations. Also shipped a production internal AI support assistant using RAG (Confluence/PDF/support docs ingestion, embeddings + vector DB retrieval) with guardrails, evaluation loops, and observability to reduce hallucinations and prevent regressions.”