Vetted AWS Professionals

“Software/product engineer who owns customer-facing internal platforms end-to-end, with deep experience building data pipeline health and data quality tooling (near-real-time alerting and ops dashboards). Strong in React/TypeScript + Python REST architectures and microservices with RabbitMQ, emphasizing reliability patterns (idempotency, DLQs, correlation IDs) and fast, safe iteration via feature flags, testing, and observability.”

“Graduate Research Assistant in Robotics at Arizona State University who built an end-to-end LLM-driven task execution framework enabling collaborative robots to convert high-level natural language instructions into safe, executable ROS actions. Implemented robust monitoring, failure detection, and automatic replanning, and addressed real-world issues like timestamp/frame-transform mismatches and heterogeneous robot interoperability using adapter nodes.”

“Backend engineer focused on scalable, secure, observable systems—built an async workflow backend with REST APIs and state persistence that improved reliability under concurrent load and cut end-to-end processing time ~40%. Strong in production security for multi-tenant systems (OAuth2/JWT, RBAC, DB row-level security) and in low-risk migrations using feature flags and canary releases, including catching and preventing cross-tenant data access issues with CI-based RLS tests.”

“Unity/VR developer who has shipped on Meta Quest (SideQuest) and built standalone PCVR medical applications used with real patients. Built a fully solo roguelike twin-stick shooter with a highly modular ScriptableObject/state-machine architecture, including custom build-time tooling to overcome Unity runtime constraints. Uses AI selectively (e.g., Claude) to generate editor tooling like a match-3 level designer to speed up level production.”

“Unity game developer who built a Twitch chat integration enabling a streamer's audience to actively participate in gameplay, boosting engagement and virality. Has hands-on multiplayer experience with Photon, including RPCs/synced variables and designing for disconnects, late-joins, and low-bandwidth data transfer, and uses Cursor/AI agent workflows to accelerate feature development while maintaining code quality.”

“Built production LLM-driven products including a job-hunt AI (job ranking + resume optimization) and an InterviewAI agentic pipeline using LangChain. Focused on practical deployment concerns like securing OpenAI usage via rate limiting and tiered quotas, and demonstrates an applied approach to choosing models, retrieval methods (RAG), and prompting strategies.”

“Unity VR developer with deep hands-on experience optimizing and debugging standalone-headset VR projects (including Android/IL2CPP and XR interaction systems), though not yet credited with a Meta Quest store ship. Built and shipped a mostly solo Unity top-down shooter (Sand Bullet) on Steam, owning core gameplay, AI, UI/input, saves, performance, and an AWS-connected companion app integration.”

“AI/ML engineer who has shipped production systems across computer vision and conversational agents: built a YOLOv8-based wheel fitment pipeline at a Techstars-backed automotive startup, focusing on sub-second latency, monitoring, and robust fallback mechanisms that drove 2–3x page view growth and +5–6k users. Also built a voice-based interview platform orchestrating Deepgram + GPT-4 Mini + OpenAI TTS with FSM-driven reliability, and has hands-on RAG experience (LangChain, hybrid retrieval, cross-encoder reranking, custom pseudo-query generation).”

“Currently at ProShare and reports building an AI/LLM-powered system deployed to production, aimed at helping with status-related difficulties and reducing misunderstandings across transactions. Also cites prior collaboration at Porsche with marketing teams, focusing on translating marketing goals into technical requirements and communicating solutions clearly to non-technical stakeholders.”

“Built and deployed a production RAG-based LLM assistant that answers day-to-day operational questions from internal PDFs/SOPs, with strong emphasis on data consistency (metadata versioning, confidence thresholds, conflict handling) and low-latency retrieval at scale. Experienced designing and orchestrating multi-agent LLM workflows (retrieval/validation/generation) and pipeline orchestration for ingestion/embedding/vector-store updates, plus iterative delivery with non-technical operations/business stakeholders.”

“Software engineer/intern who built an EV charging station management platform from scratch (TypeScript/Next.js/Node/Express/Postgres) with real-time OCPP WebSocket operations and payment processing, iterating quickly based on operator feedback. Also created an internal CloudWatch log aggregation dashboard with Slack alerts that was adopted team-wide, addressing API rate limits and log-format inconsistencies through caching, pagination, and standardized parsing.”

“Frontend-focused engineer (Shahroz) who has rebuilt and modernized products end-to-end, including a FitTech dashboard redesign from scratch with standardized tooling (ESLint/Prettier, Husky + conventional commits, unit tests, PR validation). Has delivered complex React + TypeScript dashboards involving real-time live streaming and analytics, and shipped an e-commerce PDP with integrations like Contentful and social feeds using an MVP-first, sprint-based process.”

“LLM workflow builder who has deployed a personalized GPT experience (including Delphi AI-based knowledge ingestion) and built a LangChain/LangGraph job-aggregation pipeline that ingests, normalizes/dedupes, filters, then uses an LLM to rank and summarize matches. Emphasizes production reliability with structured outputs, retries/fallbacks, metric-driven evaluation, logging/prompt versioning, and A/B testing, and collaborates with non-technical stakeholders through demo-driven iteration.”

“Built and production-deployed a Streamlit-based PDF RAG chatbot using LangChain (FAISS, embeddings, prompt templates) and OpenAI, optimizing Streamlit’s stateless behavior by caching vector DB + chat history to cut latency and API cost. Demonstrates a rigorous evaluation mindset (gold datasets, unit tests, LLM-as-judge, groundedness KPIs) and has experience communicating privacy/accuracy safeguards (RBAC, data masking, citations) to a non-technical client at Kalven Technologies.”

“Software engineer who builds workflow-centric products end-to-end, including a customer-facing module on the Trident AI content platform and an internal content workflow tool adopted as the default process. Strong in TypeScript/React + FastAPI architectures and in scaling event-driven microservices with RabbitMQ, emphasizing reliability (idempotency, DLQs) and observability (correlation IDs) to reduce outages and debugging time.”

“Frontend lead for a consumer-facing social platform, owning architecture through release. Built scalable React/TypeScript systems (Redux Toolkit, Remix) with a shared Storybook component library and strong quality gates (CI, Jest/Cypress). Experienced modernizing legacy codebases incrementally with feature flags and shipping major dashboard features with staged rollouts and close QA collaboration.”

“Frontend engineer with deep Shopify and React/TypeScript experience who has shipped real-time, high-concurrency products—most notably a live auction system on Shopify using pure JavaScript/Liquid with Pusher for instant bid updates. Also built a POS dashboard app with Redux Toolkit for real-time order/cart updates and delivered measurable storefront performance gains (~30–40% faster initial load) through modularization and asset optimization.”

“Frontend engineer who created an in-house React-like framework (“React-Wilcox”) enabling modern, event-driven UI components on extremely legacy browsers (as far back as 2002), including race-condition avoidance via batched state updates. Also does freelance work untangling AI/vibe-coded frontends for nontechnical founders, componentizing UIs and fixing routing/readability, and recently built a React+TS social app for martial artists with privacy-preserving location distance features.”

“Built and operated large-scale biodiversity/ecological research platforms, integrating 50+ heterogeneous global datasets into a unified BIEN 3 schema on PostgreSQL/PostGIS and improving data consistency by 35%. Strong production engineering background (Linux monitoring, CI/CD performance gates, Docker on AWS/Azure) plus applied AI work building a Python RAG system (0.90 precision) and halving latency with Elasticsearch.”

“Built an LLM-driven MLOps agent at SBD Technologies that automated an EV-charging prediction workflow end-to-end, integrating with real-time Kafka/FastAPI systems supporting 120K+ chargers at 99.99% event delivery. Addressed frequent schema drift by implementing SQLAlchemy/Flyway validation (60% reduction in drift issues) and deployed as Kubernetes microservices with GitHub Actions CI/CD; also has Airflow-based ingestion/crawling experience into Snowflake and stakeholder-facing delivery via a Fleetcharge PWA.”

“Backend/cloud engineer from Resilient Tech with hands-on experience deploying REST APIs and database migrations into a live ERP used by real customers while maintaining 99% uptime. Has debugged intermittent AWS container timeouts down to security group/load balancer misconfigurations, and has extended Python in an ERPNext system to meet GST/e-invoicing compliance requirements with strong customer collaboration.”

“Backend engineer who owned the API layer for an AI trust/analytics dashboard (trust scores, stability checks, public verification endpoints) using Python/FastAPI and Postgres. Has hands-on DevOps experience deploying FastAPI and Node.js services to AWS Kubernetes with GitHub Actions + ArgoCD GitOps, plus Kafka-based real-time event streaming and careful staged migration practices (shadow traffic/dual writes, rollback planning).”

“LLM/agent systems builder who deployed a production hybrid router for immerso.ai that dynamically selects retrieval vs reasoning vs generative pathways, achieving an 82% factual-accuracy lift. Deep hands-on experience optimizing local Mistral 7B inference (4–5 bit GGUF quantization, KV-cache reuse) and building reliable RAG/agent workflows with LangChain/LangGraph/AutoGen across GCP Cloud Run and AWS (ECS/Lambda).”

“Built and deployed ForensicLLM, a local domain-specific LLaMA-3.1-8B model for digital forensic investigators using RAFT + RAG over 1000+ curated research papers, with citation-aware responses and rigorous evaluation (BERTScore/G-Eval). Deployed via vLLM and Docker and validated through a chatbot survey with 80+ participants; published at DFRWS EU 2025.”