Vetted pandas Professionals

“LLM/RAG practitioner who productionized an LLM-driven customer communication and transaction understanding system at PayPal, emphasizing privacy/compliance guardrails and large-scale data normalization. Experienced in real-time debugging of hallucinations via retrieval pipeline tuning and in leading hands-on developer workshops and sales-aligned POCs to drive adoption.”

“Built and deployed an agentic RAG assistant in production to automate enterprise knowledge search and multi-step workflows with tool calling, tackling real-world issues like hallucinations, retrieval accuracy, and latency. Demonstrates strong LLMOps and orchestration depth (MLflow, Airflow, LangGraph/LangChain/LlamaIndex) plus a metrics-driven approach to agent testing/evaluation and cross-functional delivery with business stakeholders.”

“Built and shipped production LLM/AI agent systems including an NL-to-SQL query agent with semantic search and Redis-based caching, using schema-aware prompting and threshold validation to reduce hallucinations. Has orchestration experience running ML microservices on Kubernetes and automating event-driven insurance (P&C) workflows (claims/policy + fraud checks), reporting ~60% manual overhead reduction and ~99% uptime, with strong monitoring/drift-detection and business-facing Power BI reporting.”

“Built and deployed a production LLM-powered decision-support system for supply-chain planners that explains demand forecast changes using grounded retrieval from sales, promotion, inventory, and supplier data. Implemented strict anti-hallucination guardrails and latency optimizations, deployed as a real-time AWS API with monitoring, and reported ~15% forecast accuracy improvement and ~12% supply-chain risk reduction. Experienced orchestrating data/ML/LLM workflows with Airflow, LangChain/LangGraph-style patterns, and AWS Step Functions while partnering closely with non-technical business users via demos and example-based requirements.”

“Interned at Rivian where they built and deployed a production Whisper-based ASR + LLM real-time event labeling pipeline to help autonomous-vehicle engineers diagnose failures and route issues to triage teams. Also built a stateful multi-agent "Code Partner" developer assistant using LangGraph/LangChain (planner/router/coder/critique/tester) with evaluation, adversarial testing, and stakeholder-friendly communication practices.”

“Software engineer whose recent work includes co-designing and building a "Shared Profile" feature for a social event-planning app (Again, Sometime). Previously at Pure Storage, set up Docker-standardized Ubuntu/Python environments to simulate hardware testbeds and support workload/performance regression testing for other engineering teams; no robotics/ROS experience.”

“Won a machine learning contest and was placed onto a Kaiser data science team, where they built ML models for hospital bottleneck prediction and resource allocation. They later built and deployed a full-stack LLM-based “data analyst agent” (with custom orchestration plus LangChain/OpenAI Agents experience) that generates analysis code, answers questions, and produces dashboards from uploaded datasets, emphasizing rigorous evaluation sets, robustness, and healthcare security/compliance integration.”

“Computer-vision-focused candidate with internship experience at ASML (Silicon Valley) building object detection models (YOLO, RT-DETR) for SEM defect inspection. Worked end-to-end on preparing multi-resolution datasets and tuning/training strategies, noting improved performance on low-quality images when training jointly on higher-resolution data.”

“GenAI/LLM engineer with production deployments in both fintech and retail: built an AI-powered mortgage document analysis/automated underwriting pipeline at Fannie Mae (OCR + custom LLM) cutting underwriting review from 3–4 hours to under an hour with privacy-by-design controls. Also helped build Sephora’s GenAI product advisory bot using LangChain-orchestrated RAG (Azure GPT-4, Azure AI Search, MySQL HeatWave vector search), focusing on grounding, evaluation, and compliance-aware architecture choices.”

“Built a production AI-driven QA automation platform using a multi-agent architecture (MCPs + LangGraph) to run parallel website tests across multiple device environments via automated image building and containerization. Currently collaborating with restaurant operators and managers to deliver an agentic restaurant analytics system, emphasizing deep domain discovery with non-technical stakeholders.”

“Backend/DevOps-focused engineer with healthcare and financial systems experience, including an ICU readmission risk platform delivering real-time ML scores via a secure FastAPI service (PyTorch model serving, PostgreSQL, Celery/Redis) deployed on AWS with strong observability. Has hands-on Kubernetes GitOps delivery (Helm, ArgoCD, HPA) and has supported a JPMC on-prem-to-AWS microservices migration using phased validation and blue-green cutovers, plus Kafka/Avro streaming for real-time transaction processing.”

“Hands-on technical professional experienced in taking LLM/AI-adjacent integrations from prototype to production, using customer observation to refine UX and uncover edge cases. Diagnoses workflow issues in real time using logs and Sankey-style workflow analysis, and communicates fixes with clear short/long-term plans plus proactive alerting. Also partners cross-functionally to drive adoption and cost savings, including a POC around IBM Sterling Integrator that reduced licensing costs by $30K/year.”

“AI/ML engineer at J.P. Morgan Chase who deployed a production financial-risk prediction platform combining CNN/LSTM/gradient boosting on AWS SageMaker, with automated drift-triggered retraining and governance-grade fairness testing. Leveraged SageMaker Clarify plus SMOTE and LLM-generated synthetic data to improve minority-group F1 by 0.12, and communicated results to non-technical risk/ops teams via Power BI dashboards.”

“ML Engineer with recent Goldman Sachs experience building and deploying a production RAG/LLM assistant for summarization, drafting, and internal knowledge retrieval across financial, risk, and compliance documents. Designed for heavy regulatory constraints and scaled to 10,000+ concurrent users using Kubernetes-based orchestration, dynamic LLM routing, and rigorous testing (adversarial prompts, A/B tests, load simulations) with privacy controls like differential privacy.”

“Robotics software engineer focused on state estimation and localization reliability, with deep hands-on EKF tuning/validation using DGPS ground truth and integrity-risk-based uncertainty calibration. Built middleware-agnostic interfaces with ROS wrappers to enable repeatable ROS bag playback testing, and implemented CI at Caterpillar to automatically build the localization stack and run unit tests plus bag-based regressions before merge.”

“Full-stack engineer with strong DevOps/AWS production experience who builds and operates multi-agent AI systems end-to-end (Streamlit/Python through Docker/Kubernetes and ECS/Fargate). Has delivered measurable outcomes: sub-2s latency and ~92% routing accuracy for an AI wellness assistant, shipped an AI-for-BI prototype in under 6 weeks cutting analysis time ~40%, and improved pipeline iteration speed ~35% via modularization and CI/regression checks.”

“Software engineer who built and deployed OddPulse, a multi-agent LLM-powered continuous financial auditing system aimed at reducing compliance penalties by catching issues before audit cycles. Experienced with TrueAI-based agent orchestration, Airflow on GCP batch workflows, and rigorous evaluation/benchmarking (hit rate/MRR, latency/TTFT, cost) alongside security controls for sensitive financial data.”

“Completed an Amazon externship building a GPT-4 + RAG pipeline to summarize themes from hundreds of employee reviews for workforce analytics aimed at improving warehouse retention. Emphasizes production-readiness through labeled-data evaluation, source attribution for explainability, human-in-the-loop review, and rigorous data cleaning/observability to debug real-world LLM workflow issues.”

“Full-stack engineer with fintech/trading domain experience (Fidelity) and startup SaaS CRM/billing platform work (Zoho), building real-time portfolio analytics and trade-processing systems. Strong in microservices, event-driven architectures (Kafka/WebSockets), and AWS/Kubernetes operations with measurable performance gains (~34–35% latency reduction) and maintainability improvements (~40% faster deployments). Targeting a founding full-stack engineer role in NYC with meaningful equity.”

“Software engineer with strong end-to-end ownership across frontend, backend, data, and infrastructure, including real-time systems (Kafka/Postgres) and observability (Datadog). Built and productionized an AI-native RAG support assistant (OpenAI embeddings + Pinecone) with prompt/guardrail design, achieving 48% agent adoption and 30% faster responses. Experienced in legacy modernization and reliability work using feature flags, event/transaction replay, and rapid embedded delivery.”

“Built and productionized an internal LLM-powered document Q&A system at Morgan Stanley using a LangChain-based RAG pipeline (FAISS + OpenAI) with AWS ingestion (S3/Lambda), handling 100k+ pages and cutting lookup time ~35% while keeping responses under 3 seconds. Strong on reliability: automated evals/CI (pytest + GitHub Actions), CloudWatch monitoring, drift detection (prompt drift and fraud-model drift), and security controls (IAM + app-level authorization) in a financial-services environment.”

“Built and shipped production LLM/RAG systems at Mayo Clinic, including a conversational AI assistant for patient pre-consultation and a clinical-trial matching tool for doctors. Implemented HIPAA-compliant de-identification and guardrails, plus real-time feedback logging and fine-tuning that improved response accuracy by 15% and reduced admin workload by 25%.”

“Revamped a university academic calendar system into a Python-based calendar generation service, turning a weeks-long manual scheduling workflow into software that generates dozens of valid calendar combinations in under a minute. Also contributed to an Amazon search ML classifier by introducing precision/recall evaluation to better surface critical failure modes and improve prediction quality.”

“GenAI/LLMOps practitioner who deployed a production RAG-based customer service and knowledge retrieval system for a global bank using LangChain, FAISS/Azure Cognitive Search, GPT-4/Claude, and Guardrails—driving a reported 35% Q&A accuracy lift while reducing handle time and escalations. Also partnered with non-technical leaders at CVS Health to deliver ML-driven supply chain risk and inventory insights via anomaly detection, NLG summaries, and stakeholder-friendly dashboards.”