Vetted Unit Testing Professionals

“Built and deployed a production LLM-powered document Q&A system using a strict RAG pipeline (LangChain-style orchestration + FAISS) to help users query large internal document sets. Demonstrates strong reliability focus through hallucination mitigation, curated offline evaluation with grounding checks, and production monitoring (latency/fallback rates) plus stakeholder alignment via demos and business metrics.”

“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.”

“Unity gameplay/game-flow programmer with ~10 years in the games industry who has shipped on Meta Quest 1 & 2. Built a Steam-available multiplayer "Vampire Survivors"-style co-op demo largely solo in a 6-month contract, handling everything from networking and UI to performance optimization (GPU instancing) and Steam publishing.”

“LLM/AI engineer who has deployed production RAG conversational analytics and Text-to-SQL systems over Snowflake and curated data marts, emphasizing enterprise-grade guardrails for accuracy, security, and cost. Notable for a structured approach to reducing hallucinations (curated metric/table registry, SQL validation, RBAC, and citation-backed responses) and for building resilient, observable multi-step agent workflows using LangChain/LlamaIndex and Airflow.”

“ML/NLP practitioner who has delivered production systems in regulated domains, including a healthcare compliance pipeline using RAG (GPT-4/Claude) plus TF-IDF retrieval that increased document review throughput 4.5x. Also has hands-on experience improving fraud detection data quality via entity resolution (Levenshtein, Dedupe.py) validated with A/B testing, and building scalable, monitored workflows with Airflow, CI/CD, and AWS SageMaker.”

“Robotics software engineer with hands-on hardware integration who built an AI-enabled smart dog door using a Raspberry Pi, camera-based recognition (DeepFace adapted for dogs), and stepper motor control (TB6600/NEMA 17). Experienced in ROS/ROS 2 across perception-to-controls, rigorous bag-driven debugging of SLAM/navigation issues, and deploying robot software with simulation-in-the-loop testing plus Docker/Kubernetes CI/CD.”

“Frontend lead on a SaaS platform who migrated the product from React/JavaScript to Next.js/TypeScript, improving Web Vitals (including LCP), SEO, and navigation performance. Strong focus on quality and scalability via automated testing and SonarQube quality gates, plus reusable component architecture (e.g., a shared table used across ~20 pages). Built complex analytics dashboards and an AI workflow drag-and-drop canvas UI using React Flow with iterative stakeholder-driven delivery.”

“Backend engineer with open-source web3.js contributions focused on preventing costly smart-contract execution failures, plus hands-on blockchain startup experience scaling an NFT mint from a test EC2 setup to AWS Lambda/API Gateway under extreme concurrency. Built a multiplayer backend improving tick rate from 40 Hz to 105 Hz using UDP, containerization, and Kubernetes, and has healthcare production support experience across 10+ apps. Also publishes IEEE research papers and produces developer-friendly documentation that accelerates team adoption.”

“Backend engineer focused on real-time, event-driven distributed systems (Node.js/TypeScript) with strict latency and reliability requirements. Deep hands-on experience debugging concurrency issues and designing resilient workflows (idempotency, circuit breakers, compensating actions) with strong observability; familiar with ROS/ROS2 concepts and confident ramping into robotics integrations.”

“Backend lead at a stealth startup and builder of MailIQ/MailBox—an automated Gmail inbox digest + cleanup system. Designed secure multi-account email ingestion and cost-efficient LLM-based summarization, and implemented robust unsubscribe automation using Playwright + OpenAI webpage analysis (including captcha-handling) with strong safety guardrails, incremental rollouts, and rollback strategies.”

“Built a production-grade LLM evaluation and regression system that stress-tests models across hundreds of iterations, combining LLM-as-judge, semantic similarity, statistical metrics, and rule-based checks, with results delivered via stakeholder-friendly HTML reports and dashboards. Experienced orchestrating multi-agent RAG workflows using LangChain/LangGraph and event-driven GenAI pipelines in n8n integrating OCR, speech-to-text, and external APIs, with strong emphasis on reliability, observability, and explainable failures.”

“Built and productionized an LLM-enhanced version of the WeDAA platform to auto-generate microservice architecture diagrams and support code generation from user prompts, including a practical solution for non-overlapping canvas object placement via coordinate templates. Experienced in diagnosing agentic workflow failures using AWS Strands agents with feature-flagged debug logging, and frequently supports sales through tailored demos and POCs to drive adoption.”

“Indie/core Unity game developer with deep multiplayer networking experience, including client-server management and synchronization of animations/physics/player state using Photon Fusion, PUN, Mirror, and Socket.IO. Has shipped/implemented multiple networked game types (fish, poker, chess, shooter) and has integrated AI-driven features like TTS and 3D character lip-sync (SALSA + blend shapes) using guidance from tools like ChatGPT.”

“Frontend engineer who led Curion’s end-to-end UI architecture for a real-time meetings/elections product, emphasizing scalability, testing, and CI/CD. Has built complex React+TypeScript dashboards (Redux) and improved a Flutter codebase with DDD and dependency injection, enabling smoother third-party swaps like Zoom to LiveKit and rapid delivery of Brazil-specific payment methods (PIX/Boleto).”

“Backend/full-stack engineer with experience building customer-facing contact-center automation (agent assignment) and internal editorial/data operations APIs for life-sciences ontology management. Strong in microservices and event-driven systems (Spring Boot + Kafka), third-party integrations (Genesys/Five9), and pragmatic iteration via MVP scoping, tight stakeholder demos, and observability-focused reliability.”

“Software engineer who deployed and stabilized a real-time analytics platform at Senecio Software, focusing on production reliability, observability, and performance under load. Experienced debugging issues spanning distributed services and networking (e.g., tracing timeouts to packet loss from misconfiguration) and extending Python (FastAPI/Django) APIs for customer-specific analytics features in a configurable, maintainable way.”

“Backend/applied AI engineer from Cloud Rack Systems who built production GenAI/RAG and data platforms on Azure/Databricks at enterprise scale (2.5M records/day). Known for making LLM systems behave like deterministic services via strict retrieval contracts, citation-based validation, and strong observability—shipping a knowledge assistant used daily by 50+ users while driving hallucinations near zero and materially improving latency and cost.”