Vetted LLM Integration Professionals

Hannah Aron

Screened

Senior Full-Stack Engineer specializing in Python web and cloud applications

Hayward, CA8y exp

“Full-stack engineer with strong Python/React experience who has built systems from scratch, including a custom POS platform as the sole initial engineer. They also bring applied experience across IoT reward platforms, HR matching/search systems, and LLM-powered automation products, with a track record of improving reliability and speed through thoughtful architecture decisions.”

Jookwang Jung

Screened

Staff Software Engineer specializing in AI-native platforms and full-stack systems

Los Angeles, CA20y exp

“Founding engineering lead and player-coach who built a small cross-functional team around an AI-first development model, increasing execution speed by more than 3x through hands-on coaching and human-in-the-loop practices. Has led architecture for a multi-tenant platform and built an AI system for fashion businesses that generates content, imagery, and operational recommendations, combining technical depth with product and UX judgment.”

“Backend Python engineer who owned the full backend build of an AI-driven platform for UK golf clubs, including FastAPI microservices, vector search, and a tuned LangChain+Pinecone RAG pipeline focused on cost and hallucination reduction. Experienced deploying Django/FastAPI/Flask stacks on AWS-backed Kubernetes with GitOps/ArgoCD-style delivery, plus executing legacy-to-AWS migrations and building Kafka-based real-time analytics pipelines.”

Deeptanshu Patel

Screened

Intern Software Engineer specializing in LLM security and automation

Plano, TX0y exp

“Built and shipped a production LLM safety-testing agent using Gemini with support for running multiple LLMs, focused on fast (<5s) execution and clear failure-mode reporting. The tool helps smaller companies evaluate whether their LLMs respond safely by grading outputs and tuning scoring consistency.”

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.”

Kratin Bhardwaj

Screened

Senior Product Designer specializing in AI-native products and enterprise SaaS

Denver, CO5y exp

“Product designer at FRCC with strong systems thinking and front-end fluency, leading end-to-end redesigns across content and AI workflow products. Notable for pairing measurable UX gains (54% to 91% task success, 12% subscription growth) with faster delivery, including compressing design-to-production from 8 weeks to 3 weeks and shipping an AI request-routing product live in 2.5 weeks.”

“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.”

“Gameplay/network engineer based in Argentina who has shipped across Unity and UE5, with standout work in deterministic simulation, authoritative multiplayer, and fully local AI-driven NPC systems. Particularly compelling for teams building systemic gameplay or real-time interactive experiences: they replaced Unity physics with a custom deterministic race pipeline, improved WebGL load performance, and later built an engine-agnostic local LLM/TTS/lip-sync stack for conversational NPCs.”

“Full-stack engineer who has owned both institutional and personal products end-to-end, including Rutgers' myCommunity platform used by 70,000+ students. Particularly strong in production systems, data synchronization, authentication, and third-party API integrations, with a pragmatic approach to shipping, observability, and UI modernization.”

“Built and deployed a Unity-based, NSF-funded medical interaction system for the University of Houston MRI Lab, combining speech recognition, LLaMA-based function calling, and real-time simulation controls. Particularly strong in taking experimental AI systems from discovery through stabilization, with measurable impact including roughly 50% faster task completion than traditional point-and-click workflows.”

“Full-stack engineer who built WordCon, an AI-powered vocabulary learning platform, end-to-end across React/Next.js, Python, AWS, and GenAI services. Particularly strong at turning ambiguous AI product ideas into structured, scalable systems by combining deterministic learning logic with LLM-powered personalization, and has additional experience modernizing legacy PHP systems into React/Node architectures.”

“Early-career frontend/full-stack engineer with internship experience at EventEase, where they built a live scoring and tournament-operations platform for charity golf events. They stand out for owning complex multi-user browser UIs, making thoughtful architecture trade-offs, and translating real user feedback into features like responsive admin tools, moderated photo sharing, and team/organizer chat.”

“Full-stack engineer with experience building healthcare scheduling, telehealth, reimbursement, and agent workflow systems using React, Node.js, MySQL, TypeScript, and GraphQL. Stands out for combining hands-on product design in ambiguous environments with measurable technical impact, including a 40% performance improvement and reduced LLM costs through batching and backend optimization. Also brings manufacturing/MES experience and a strong habit of reshaping products based on direct user feedback.”

“Founding engineer at a recruiting SaaS startup who helped build the product from scratch through Series A, then went on to build a production compliance filing platform handling regulated BOI/RRE workflows. Strong Rails-centric full-stack engineer with hands-on experience in startup ambiguity, third-party integrations, bulk processing, and audit-friendly data systems.”

Kathan Patel

Screened

Mid-level Generative AI Developer specializing in Python and LLM applications

5y exp

“Currently working on Kavia AI, an end-to-end AI coding platform that lets users generate enterprise applications from prompts and existing codebases via SCM integrations. The candidate has hands-on experience across the GenAI stack—prompt engineering, LangGraph-based multi-agent orchestration, RAG, knowledge graphs, FastAPI, and AWS monitoring—with a focus on making software creation accessible to non-technical users.”