Vetted Playwright Professionals

Aaron Li

Screened

Junior AI/ML Engineer specializing in production LLM systems and RAG

Atlanta, GA2y exp

“LLM/document AI engineer who owned a production-grade contract extraction pipeline at CORAMA.AI, ingesting PDFs and dynamic JavaScript sites from 1,000+ government sources. Built a hybrid deterministic+LLM system with two-phase prompting, Pydantic guardrails, confidence scoring, and human-in-the-loop review—cutting error rates from ~35% to <5% and processing 50k+ documents at ~95% accuracy. Also built clinician-in-the-loop orchestration in research, reducing manual labeling time from 3–4 hours to ~50 minutes.”

Aakash Khepar

Screened

Mid-level Full-Stack AI Engineer specializing in agentic AI systems

Tempe, AZ4y exp

“Full-stack engineer with strong ownership across production SaaS and AI agent systems, including a multi-tenant enterprise analytics product at Fractal Analytics and an archive intelligence platform for a real nonprofit. Stands out for combining deep backend/system design, secure AI/RAG implementation, and rapid zero-to-one execution—plus multiple hackathon wins and leadership roles.”

“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).”

Seung Jun Kim

Screened

Mid-level UX/Human Interface Designer specializing in design systems and UX research

4y exp

“Product/UX designer with industrial domain experience designing an end-to-end "factory mode" vehicle software experience for assembly-line workers, optimized for speed, flat navigation, and multi-device responsiveness across different plants. Combines rigorous field research and SME collaboration with strong front-end skills (HTML/CSS/TypeScript/React), including coding components to demonstrate feasibility and keep features in scope; also has accessibility-focused telehealth capstone work for d/Deaf and hard-of-hearing users.”

“Built and owned end-to-end production systems for a healthcare platform, including a predictive task recommendation feature (React + FastAPI + ML on AWS ECS) that cut backlog 20% and saved coordinators ~10 hours/week. Also productionized an AI-native RAG system (vector DB + LLM) delivering 40% faster query resolution, and led phased modernization of a monolithic FastAPI service into async microservices using feature flags and canary releases.”

“Built production-grade Python systems in a medical/imaging context, including an image feature extraction and survival prediction microservice with strong testing, validation, and observability practices. Also developed a Playwright-based autonomous job application agent that handled dynamic UIs and anti-bot challenges with stealth tooling, proxies, and human-in-the-loop escalation.”

“Backend engineer who built and evolved an internal multi-agent AI research platform (Electron + FastAPI) integrating OpenAI, focused on fast, reproducible experimentation with strong observability and run metadata for debugging. Has led incremental backend refactors with feature flags and parallel validation, and brings production-grade access control expertise from ServiceNow (table/field ACLs and row-level-style enforcement).”

“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.”

Alex ZhuZhou

Screened

Intern Full-Stack Software Engineer specializing in AI/LLM platforms and data systems

Berkeley, CA2y exp

“Backend/LLM engineer with experience productionizing RAG systems (legal-case natural language querying) and optimizing for latency/cost, including a reported ~40% reduction via Redis caching and batching. Built monitoring and real-time debugging workflows (FastAPI, structured logging, correlation IDs, sandbox repro) and regularly delivered technical demos/workshops. Also partners with BD/sales to translate LLM capabilities into business value, including ESG-metric extraction from corporate filings.”

Joseph Villanueva

Screened

Senior Software Engineer specializing in full-stack SaaS and Healthcare IT

San Francisco, CA8y exp

“Product-minded software engineer from Gusto who has shipped internal AI agent capabilities and end-to-end user-facing features across frontend and backend. Stands out for making pragmatic architecture tradeoffs—moving from OpenAI prototypes to deterministic systems when accuracy, latency, and uptime mattered—while still improving LLM workflow quality and reducing tool-calling errors by 15%.”

Prajit Mohan

Screened

Junior QA Engineer specializing in test automation for web applications

Oakland, CA3y exp

“QA automation engineer with healthcare web experience who owned an end-to-end automated test suite (Java/Cucumber/Selenium and Cypress) and integrated it into CI/CD (Jenkins to GitHub Actions, qTest DoD gates). Known for boosting regression coverage to ~93%, stabilizing flaky Cypress tests, and catching production-impacting pipeline/environment redirect issues through workflow updates and cross-browser/regional scenario testing.”

“AI-focused engineer who treats models as tightly controlled collaborators rather than autonomous replacements. Built and led a LangGraph-based multi-agent research system with separate stages for decomposition, retrieval, synthesis, and validation, emphasizing modularity, debuggability, and robust failure handling.”

“Front-end/UI engineer who built and standardized a complex metadata component system for 2,500+ banking users across 40+ internal product surfaces. Stands out for combining design-system architecture, browser-level CSS expertise, and workflow-sensitive UX for demanding financial users, including a token system that resolved 488 style references and a reusable responsive component library adopted across five product areas.”