Vetted LLM Integration Professionals

“Amazon engineer who built a production AI agent platform (Python/AWS Strands on Bedrock) that lets teams create tool-using, multi-agent workflows—e.g., agents that auto-triage and resolve customer support tickets by reading internal documentation and collaborating with a research agent. Previously worked in Deloitte on IAM using Ping Identity/Ping DaVinci orchestration, and applies orchestration thinking plus structured evaluation (LLM-as-judge, surveys, automated tests) to improve agent reliability.”

“Founding engineer for an AI product (“world’s first funny AI”) who designed and implemented the full-stack architecture (React/TypeScript + Node) and migrated production from Vercel to AWS. Shipped a Lambda-based image pipeline that eliminated lag/missing images and brought page load times to under a second, and has hands-on experience integrating multiple LLM providers (OpenAI, Claude, Gemini, Grok) with structured-output and self-check reliability techniques.”

“Senior software engineer (5+ years) from Walmart Global Tech who owned and operated high-scale supplier inventory submission systems, including a microservice handling submissions up to 500k items and a data platform processing ~10TB/day. Strong in AWS/Kubernetes (EKS), Kafka/Spark streaming + batch pipelines, and production operations (on-call, metrics/alerting), with demonstrated performance wins (30% faster responses, 50% faster processing).”

“Full-stack product engineer with hands-on ownership across React/TypeScript, serverless backends, and Postgres, combining technical depth with strong UX instincts. Stands out for measurable impact: improved a slow query from seconds to under 200ms and increased onboarding completion by about 25%, while also building reusable platform primitives and scalable multi-tenant configuration systems.”

“Unity/C# game engineer with about 3 years of experience who owned a high-impact runtime content delivery platform at Zynga/Singa powering LiveOps releases for roughly two years. Their work cut app size by 35-40%, removed a 25K daily activator drop on release days, improved load times by 25%, and supported a feature that drove 10% quarterly revenue growth.”

Sergio Nunez

Screened

Senior Unity Engineer specializing in XR, mobile, and AI avatar experiences

Los Angeles, CA9y exp

“Unity/C# game engineer from Genies who built the avatar wearable customization system for Silver Studio and supported AI companion features through client-side LLM integrations. Stands out for combining clean architecture, analytics-driven product thinking, and practical optimization work across latency, AI cost controls, and mobile performance.”

Farhan Shahbaz

Screened

Senior Software Engineer specializing in cloud infrastructure and platform engineering

New York, NY4y exp

“Backend engineer with deep experience in security and access-management platforms at JPMorgan Chase, including owning automation for migrating 50+ engineering teams from CyberArk to HashiCorp Vault. Stands out for combining regulated-environment rigor, infrastructure automation, and production operations with practical AI integration in internal access workflows.”

“Product designer with hands-on front-end implementation experience who has owned complex flows end-to-end at Wix and Intuit, including a live keynote demo for Wix’s first developer conference and a tournament-based inner-source readiness program across global AI/data teams. Particularly strong at turning ambiguous briefs into structured experiences, using design systems rigor, interaction design, and implementation fluency to ship polished, understandable products.”

“Product leader at VicRoads who rebuilt the Custom Plates digital portfolio, including an AI-powered pricing and recommendation platform that drove more than 20% revenue uplift. Stands out for combining commercial product thinking with explainable AI, regulatory compliance, and legacy-system modernization in a government-related environment.”

Melissa Bennett

Screened

Executive engineering and AI leader specializing in healthcare AI and startup scaling

Los Angeles, CA21y exp

“Engineering leader who has built teams and products from scratch in both healthcare AI and consumer tech. Most notably, they grew Thrive AI Health’s engineering org from 0 to 20 and led delivery of a multimodal, multi-agent AI health coach—including a real-time voice experience piloted with Eli Lilly—while previously scaling Sweetgreen’s mobile ordering platform into a major revenue channel.”

Pujan Parikh

Screened

Staff Front-End Engineer specializing in enterprise cloud and AI-driven applications

Redwood City, CA8y exp

“Frontend-leaning architect with deep React/TypeScript expertise who has repeatedly owned platform-level problems across Oracle Health, Oracle Cloud, and Veritas. Stands out for building cross-plugin routing standards for a next-gen EHR, high-scale real-time observability dashboards, and even stepping into backend/AI infrastructure design with Kafka- and RAG-based systems.”

“Backend engineer at Goldman Sachs who deployed internal LLM-powered utilities to summarize operational logs/tickets, with a strong emphasis on data sensitivity and reliability. Built deterministic workflows with template-based prompts, confidence checks, and rule-based fallbacks, and used monitoring plus failure-rate metrics to tune performance; also has hands-on Temporal orchestration experience for resilient async backend jobs.”

“Backend engineer with strong AWS/CI/CD experience (multi-repo deployments, Lambda + core app, immutable ECR and image promotion) and a published master’s thesis building an ML framework for Solar PV energy prediction and CO2 reduction impact modeling using ensemble and meta-learning approaches benchmarked against SAM.”

Subbu Paravatareddy

Screened

Engineering Leader specializing in cloud modernization and AI/ML integration

Emeryville, CA21y exp

“Player-coach engineering leader focused on buyer/distribution product lines, building scalable purchasing/planning frameworks and modernizing workflows. Drove performance and reliability improvements via queue-based async architectures, external API redundancy, and CI/CD automation, and has led production incident response (cache-related) with follow-up playbooks and monitoring. Experienced in high-growth/startup environments, combining hands-on delivery with mentoring, 1:1s, and performance coaching.”

Jen-Hung Chang

Screened

Mid-level Software Engineer specializing in cloud infrastructure and distributed systems

Hsinchu, Taiwan4y exp

“Backend/platform engineer who built an AI RAG system on FastAPI/Postgres/AWS with 10+ microservices, vector search optimization (ANN + two-stage re-ranking), and GitOps-driven CI/CD that cut deploy time from hours to minutes. Also deployed Java identity services on Kubernetes at TSMC for 200K+ users using ArgoCD/Azure Pipelines, and built a reliable real-time IoT pipeline (MQTT/Node/MongoDB) with strong consistency controls.”

“Candidate takes a disciplined, developer-in-the-loop approach to AI-assisted coding, using AI primarily for brainstorming, suggestions, and optimization while retaining full ownership of architecture and final code decisions. They also actively stay current on AI developments through research papers, communities, and emerging tools.”

“5-year .NET full stack developer who has applied AI-assisted development in an enterprise Cisco environment, using tools like GitHub Copilot and ChatGPT to accelerate microservice API delivery while maintaining architecture, security, and code quality standards. Notably reports a roughly 30% reduction in development time on a customer policy management/claims processing project through disciplined use of AI for boilerplate, testing, and design validation.”

“Candidate brings practical GenAI engineering experience with a disciplined approach to AI-assisted development. They have designed lightweight multi-agent workflows for a RAG-based support copilot, including retrieval, relevance validation, response generation, and groundedness checks to reduce hallucinations.”

“Product leader with deep experience modernizing complex, integration-heavy platforms in legal tech and healthcare. Notable for redirecting a legacy Thomson Reuters product from a cosmetic UI rewrite into an API platform that unlocked new markets, and for launching an AI-assisted 340B rebate product at SunRx with a 90% successful auto-resubmission rate. Combines strong technical depth, regulated-industry domain knowledge, and team-building experience.”

“Full-stack engineer who built an LLM-powered productivity web app (LifeOS) end-to-end with TypeScript/Next.js, Prisma, and Postgres, emphasizing fast iteration with stable API contracts and an isolated AI service boundary. Also built a security/compliance login-verification workflow at Medpace used within an internal admin portal for thousands of employees, and has AWS experience orchestrating batch GPU workloads with robust retry/idempotency patterns.”

“Backend engineer who built and owned an AI-powered SMS survey platform for a nonprofit serving at-risk communities (internet-limited users), using Cloudflare Workers + Twilio and a state-machine survey engine. Scaled it to ~10k active users with near-zero downtime, added English/Spanish support, and iteratively improved LLM behavior (Claude 3.7 Sonnet) to handle nuanced, real-world SMS responses reliably.”

“AWS Solutions Architect intern who advised customers on securing a multi-tenant LLM-based SaaS, including isolation strategy tradeoffs and production guardrails against prompt injection. Has experience investigating a prompt-injection incident using logs/traces and TTP-style documentation, and designing scalable SDK/agent integrations via asynchronous worker architecture with prompt versioning.”

“Built and owned "Cortex," an AI agent that helps users understand large GitHub repositories by mapping architecture and relationships between files/folders in minutes. Implemented an agentic, multi-stage prompt decomposition approach and validated it across open-source repos, while also doing legacy service modernization work involving dependency upgrades and refactors.”