Vetted LLM Integration Professionals

Vishnu Priyan Sellam Shanmugavel

Screened

Mid-Level Applied AI Engineer specializing in LLM services, RAG, and OCR/NLP extraction

Arlington, VA4y exp

“Backend/platform engineer who built and evolved a large-scale healthcare document processing system (OCR + LLM orchestration) in Python/FastAPI on Google Cloud (Cloud Run, GCS, Firestore), processing ~1.5M files per batch and tens of millions overall. Emphasizes reliability and operational safety via deterministic IDs, idempotent state machines, strong observability, and self-healing reconciliation, plus disciplined migrations using dual-run validation and incremental rollouts.”

“Backend engineer at PlatePost who built an AI-driven food pairing/recommendation feature for restaurants using Google Gemini, shipping quickly by caching results with a 24-hour refresh and manual override. Emphasizes practical reliability/security patterns (logging, error handling, tenant-scoped queries) and proactively caught an accessibility issue via screen reader testing.”

“Built and shipped production LLM agents for real-time, high-concurrency conversational systems, including a RAG-based pipeline with dynamic multi-provider routing and failover that achieved 99.99% reliability and sub-800ms latency. Also architected a UAV telemetry chatbot with tool-calling (anomaly detection/summarization), strict schema validation, and robust eval/monitoring loops, cutting tool-call errors by 30% and reducing operational costs by 90%.”

Rizwana Shaik

Screened

Mid-level Full-Stack Software Engineer specializing in cloud-native apps and AI copilots

Dallas, TX4y exp

“Internship project building and deploying a LLaMA-based, RAG-enabled copilot inside a Professional Services Automation platform, enabling natural-language navigation, text-to-SQL reporting, and project/resource/budget insights across multiple modules. Addressed real production issues like context drift and vague queries with hybrid search, metadata enrichment, and an intent classification/rewriting layer, orchestrated via Apache Airflow—ultimately cutting PMO reporting time by 40%.”

Emmanuel Eruck

Screened

Senior Full-Stack Software Engineer specializing in AI and FinTech

Toronto, Canada8y exp

“Frontend engineer who led the mentorAi SaaS platform UI end-to-end at IBL.ai, building real-time React/Redux experiences backed by WebSockets and scaling quality with Playwright E2E tests in GitHub CI. Also worked at Paymentology for ~2 years on fintech features (token management, Visa card creation/assignment and funding flows), modernizing an existing React codebase by introducing TypeScript and strengthening CI/coverage with SonarQube to reduce deployment bugs.”

Swapnil Sanjay Pawar

Screened

Junior Full-Stack Software Engineer specializing in GenAI and web platforms

Atlanta, GA2y exp

“AI/software engineer with hands-on experience deploying an LLM-powered quiz generation platform for students, integrating Python services with Gemini APIs plus frontend and database components. Emphasizes production-grade reliability through observability, schema validation, async processing, and performance tuning under high concurrency, and has collaborated with product/operators (e.g., at Colombo AI) to translate real-world constraints into scalable technical solutions.”

Vitor Souza

Screened

Senior Game Developer specializing in multiplayer, XR/VR, and real-time networking

Lynchburg, VA8y exp

“Unity/C# gameplay engineer who has owned end-to-end systems for live-service AR and shipped VR (Meta Quest) and mobile titles. Built a hybrid LLM-driven real-time NPC interaction pipeline (STT/LLM/TTS) with streaming SSE, strict JSON contracts, and state-machine execution for stability, plus a custom UDP/TCP authoritative multiplayer stack deployed on AWS EC2 with live monitoring and rapid hotfix capability.”