Vetted LLM Integration Professionals

Naveen K

Screened

Mid-level Full-Stack Software Engineer specializing in AI agents and RAG workflows

San Francisco, CA3y exp

“Candidate is highly focused on AI-native software development, using tools like GitHub Copilot and OpenAI models within structured plan-code-review-test workflows. They stand out for designing multi-agent coding systems with planner, coder, and tester roles, and for applying tech-lead style governance through constraints, quality gates, and validation-first practices.”

Austin Pierce-Ptak

Screened

Mid-level Software Engineer specializing in full-stack and ETL systems

Seattle, WA5y exp

“Backend engineer with end-to-end ownership experience across enterprise SaaS and high-volume data systems, including PostgreSQL/.NET services at Visual Lease and ETL pipelines at Broadridge processing millions of records for Fortune 500 clients. Stands out for combining production support, observability thinking, and pragmatic architecture tradeoffs, while also experimenting with LLM-powered job application automation using Claude.”

“Backend-focused engineer with hands-on experience deploying AI-driven document processing and RAG-based workflows using Python, LangChain, FAISS, and REST APIs. Has owned projects from requirements through post-launch monitoring, including debugging production retrieval issues and building reliable pipelines for messy PDFs/scans and compliance-oriented document analysis.”

“Software engineer who built and open-sourced reusable React/Node.js modules (chat, auth, caching) from an AI education platform, emphasizing intuitive APIs and strong documentation. At TCS, improved a healthcare scheduling platform by diagnosing SQL/server bottlenecks and redesigning database + caching, cutting appointment load times by ~40% and reducing support complaints.”

“Built and monetized an object-identification app end-to-end (FastAPI backend, HTML/JS frontend, SQLite→Postgres, auth, and an iOS wrapper via Capacitor/Xcode with Apple privacy/policy compliance). Also productionized an AI-native geospatial metadata/QA assistant using LLM+RAG plus deterministic Python validation, measuring impact via time-to-first-pass review and rework rate, and has experience modernizing legacy GIS workflows and delivering across USDA/FEMA-style teams with disciplined Jira-based execution.”

Darshan Togadiya

Screened

Mid-level Full-Stack Engineer specializing in cloud-native web apps

Rancho Cucamonga, CA5y exp

“Full-stack engineer in an early-stage startup who built an EV charger monitoring and payments dashboard from scratch, owning UI/UX (Figma), React frontend, Node/Postgres APIs, and production deployment/ops (Firebase + AWS). Demonstrated measurable impact (40% fewer reconciliation errors) and strong reliability chops through multi-source energy/payment ingestion, idempotent pipelines, and CloudWatch-driven incident resolution.”

Haritha Peddi

Screened

Mid-level SOC Analyst specializing in SIEM detection, threat hunting, and incident response

USA5y exp

“Backend/AI engineer with production experience in payments/reporting systems and high-scale Node/NestJS services on AWS (ECS/ALB) using PostgreSQL, Redis, Kafka, Prisma, and Datadog. Shipped applied AI features including a Zendesk-embedded support copilot (summarization, draft replies, internal doc retrieval, playbook next steps) and an LLM-driven ops workflow agent with robust error taxonomy, retries/escalation rules, and auditability.”

“Application-focused full-stack engineer in the clinical/health domain who shipped an LLM-powered clinical note summarization workflow end-to-end (FastAPI + Postgres + Kafka workers + React/TypeScript UI) with strong attention to security, auditability, and clinician trust. Has hands-on AWS/EKS operations experience and has resolved real production latency/scaling issues through async processing, query/index tuning, caching, and horizontal scaling.”

“Backend engineer with hands-on experience scaling a CVE processing platform by re-architecting it into a Kafka-based distributed system, boosting throughput to 200k+ records/min while designing for HA, deduplication, and fault tolerance. Also led a Flyway-driven migration affecting 15M+ records with staged dev→stage→prod rollout, and has implemented production security patterns (Auth0, OAuth2/HTTPS, AWS IAM RBAC) including least-privilege hardening.”

“AI engineer at Cleveland Clinic building production LLM/NLP systems for radiology documentation, focused on HIPAA-aware, real-time performance across ~298 campuses. Re-architected infrastructure with AWS event-driven services to handle scaling and improved SLA compliance ~40%, and complements this with a personal multi-agent debate system (CrewAI) using local Llama/Mistral plus rigorous evaluation (A/B tests, red teaming, observability).”

“Backend engineer who built an AI RAG quoting system for the fastener industry, reducing quote turnaround from weeks to ~30 minutes and raising retrieval accuracy to ~90% by solving a semantic-collision issue with a parent-document retrieval design. Strong in production AWS integrations (Cognito auth, S3 pre-signed uploads), performance optimization (multithreading/out-of-core), and real-time streaming (Kafka/Spark Kappa architecture achieving sub-second latency), plus Kubernetes logging and GitHub Actions CI/CD to ECR.”

“Built and deployed an enterprise RAG application at Centene to help clinical teams retrieve insights from large internal policy document sets, cutting manual research by 30–40%. Implemented custom domain-adapted embeddings (SageMaker + BERT transfer learning) and hybrid retrieval (BM25 + Pinecone) to drive a 22% relevance lift, and ran the system in production on AWS EKS with CI/CD, MLflow, and Prometheus monitoring (99% uptime, ~40% latency reduction).”

“Backend engineer with airline operations domain experience who modernized flight-ops systems from batch updates to real-time streaming on AWS (Kafka + Spring Boot microservices), improving latency and stability through metric-driven tuning and idempotency. Also shipped a production LLM decision-support component using RAG over operational logs and internal procedures, with strong guardrails and an evaluation/regression loop to reduce hallucinations and enforce grounding.”

Umair Khokhar

Screened

Director-level Engineering Leader specializing in AI Platforms for Enterprise B2B SaaS

San Francisco, CA15y exp

“Technical leader/player-coach who architected and shipped an end-to-end computer vision pricing system for a major North American auto seller, using Go + Ray + AWS SageMaker in a low-latency distributed inference architecture. Strong in production governance (logs/tracing/guardrails/AppSec), reliability incident ownership (DNS limits affecting 20% traffic), and measurable delivery acceleration (deployment cycle 16→4 days; delivery speed 5→2 days) through process optimization and AI-assisted enablement.”

“Full-stack engineer who has owned an operations/reporting dashboard end-to-end, spanning React/TypeScript frontend architecture, ASP.NET Core APIs, and SQL data access. Stands out for combining strong UI performance optimization with pragmatic backend decisions, post-launch monitoring, and 0→1 startup platform building that improved API speed by 35% while supporting 2,000+ transactions per hour.”

Jason Gagne

Screened

Executive full-stack engineer specializing in AI, EdTech, and zero-to-one platforms

Remote, USA10y exp

“EdTech-focused startup builder and technical leader who built writing.io from zero to one and scaled it to 200k learners, later creating MindyRoad, an AI-heavy homeschool platform originally for his own family. Former Chief Architect at ParentSquare, bringing a rare mix of hands-on product execution, architecture leadership, and deep enthusiasm for transforming legacy industries.”

“Entrepreneurial product builder who created chaintrigger.com in response to early Web3 demand for real-time on-chain event reactions, offering an alternative to The Graph Protocol and achieving adoption among games and other Web3 projects. Currently developing new tools, dogfooding internally, and building distribution via personal network and a niche Twitter/X following to gather feedback and iterate quickly.”

“Built a production LLM-powered crypto trading platform in PHP/Laravel that combined RAG, market data, sentiment signals, and operator review workflows to generate buy/sell recommendations. Stands out for a disciplined approach to agentic systems: the application owns orchestration, risk controls, audit trails, and approvals, while the LLM is treated as a bounded advisory component rather than the control plane.”