Vetted AJAX Professionals

“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).”

“Game QA professional with AAA open-world shipping experience, owning high-impact quality risks like save-data corruption, progression blockers, performance drops, and multiplayer desync. Demonstrates strong systems thinking and exploit prevention (e.g., reproduced and helped fix a reward-duplication race condition using network interruption + rapid input), with disciplined JIRA/TestRail workflows and evidence-driven bug reporting.”

“Backend-leaning full-stack engineer in fintech/payments who shipped an end-to-end Stripe payments + webhook system for a financial microservices platform, emphasizing ledger accuracy via idempotency, transactional writes, retries, and DLQs. Also delivered a real-time React/TypeScript payment status dashboard informed by user interviews, and improved production performance by 35% p95 latency through PostgreSQL tuning and Redis caching on AWS.”

“Frontend/fullstack lead who inherited a messy psychological app with production issues, drove a rapid stabilization (2–3 weeks) and major performance/architecture overhaul (Redux Toolkit, memoization, caching, lazy loading, CDN offload to S3/CloudFront). Also owns delivery and infrastructure practices (multi-env, Docker, GitHub Actions CI/CD, AWS ECS + load balancing) and led a 1-week POC for an AI-powered trucking management system (app.neblo.ai).”

“Built and deployed a production AI-powered personalized learning platform (Django + FastAPI) featuring an LLM+RAG tutoring assistant and automated grading. Demonstrates strong applied LLM reliability engineering (structured JSON outputs with Pydantic validation, hallucination control via FAISS-based RAG thresholds and refusals) plus scalable async microservice design and Airflow-orchestrated ETL across AWS/GCP.”