Vetted Large Language Models (LLMs) Professionals

“AI/full-stack engineer in gaming analytics who joined Omnic.ai at a 2-person stage, helped grow with the company, and built both backend and frontend for real-time gameplay analysis products. He combines computer vision production experience with LLM/RAG systems work, and has already led 4 employees while shipping 12 models in a fast-moving startup environment.”

Sokhnadiarra Ndiaye

Screened

Mid-level founder and community growth leader specializing in education and startup partnerships

New York, NY8y exp

“Founder-operator who built and pivoted Muneko from a media translation startup into a media distribution platform for emerging-market film and TV, securing LOIs, pilots, and high-profile industry relationships. Earlier served as COO of a NYC policy advocacy organization at age 18, helping scale it from a small team to 50-70 active members while driving major events and public visibility.”

“Full-stack/product-minded engineer with strong React/TypeScript depth who has owned systems end-to-end, from UI architecture to backend services and data design. At Qualcomm, they built both a telemetry dashboard and an ML model drift monitoring platform for 20+ edge models, including post-launch tuning that cut false positives by 60%. They also demonstrate 0→1 startup execution by solo-building a production RAG document Q&A platform with JWT auth, Stripe gating, and sub-300ms retrieval.”

“Backend engineer with experience evolving a high-volume agricultural loan processing platform (APMS) at HDFC Bank, emphasizing transactional integrity, auditability, and modularity while integrating with credit bureaus, document management, and risk engines. Also improved automation/reporting robustness at Trend Micro by catching duplicate-event retry edge cases and adding idempotency safeguards.”

“Small-team builder of Promethium’s “Mantra” next-gen agentic text-to-SQL engine, using vector DB + LangGraph tooling and SQL validation/evaluation to improve query accuracy. Experienced in diagnosing production LLM workflow failures via LangSmith traces and in running hands-on developer workshops and pre-sales POCs with live debugging and real customer data.”

“Engineering Manager/player-coach leading Data Infrastructure, ML/DS, and AI Engineering pods who recently shipped multiple production agentic GenAI features. Built privacy-preserving LLM workflows (PII redaction via Microsoft Presidio) and drove an AI expense-approval agent from ambiguous ask to GA, cutting approval time from ~2.5 days to <4 hours with >85% accuracy. Also owned a major LLM cost overrun incident and implemented cost observability plus circuit breakers to prevent runaway agent loops.”

“Built an NYU software engineering capstone called “Smart Cash AI,” a multi-agent LLM-powered web app that curates offline-ready podcasts/articles/videos/news based on user preferences and commute schedules. Architected agent orchestration (discovery/downloader/summarizer), real-time progress via WebSockets, and an ETL normalization layer across RSS/YouTube and other sources with GUID-based deduplication, retries, and failure isolation to keep the system predictable.”

Chris Colinsky

Screened

Executive Technology Leader/CTO specializing in data platforms, AI agents, and e-commerce/payments

Los Angeles, CA23y exp

“Engineering leader with hands-on coding time who has driven major commerce and data-platform transformations: defined goop’s omnichannel strategy, unified payments to Square, and rebuilt real-time NetSuite inventory flows plus forecasting tools. Currently reorganized engineering into Product/Data/Support teams to hit aggressive seasonal roadmaps, and led a data-lake/medallion ELT refactor feeding embedded analytics (Tinybird) with improved reliability and cost efficiency; also accelerates onboarding via AI coding tools in a serverless, event-driven architecture.”

“Lead engineer/designer behind The Washington Post's internal live-tracker tooling and election coverage interfaces. They combine cloud architecture, frontend/data-viz craftsmanship, and close newsroom stakeholder collaboration to ship real-time, high-traffic journalism products that improved internal efficiency and supported major audience and subscriber outcomes.”

Ajay Desai

Screened

Mid-level Full-Stack Software Engineer specializing in FinTech and backend platforms

USA4y exp

“Built an AI-native legal research platform that automated analysis across 100,000+ dense legal documents, combining LLM workflows, async backend architecture, and conversational retrieval in production. Also brings cross-domain experience in investment-analysis agents and healthcare claims/billing systems, with a strong emphasis on reliability, deterministic orchestration, and safe handling of messy operational data.”

“Backend/AI engineer who has owned production agentic systems end-to-end, including a CRM-integrated multi-agent financial workflow at Wow Payments that cut latency by 83% and achieved 98% uptime. Also built an AI real estate product ('Site IQ') by turning vague stakeholder goals into a geospatial autonomous agent using RAG, rapid prototyping, and tight validation layers around GPT-4 outputs.”

Nadia Elinbabi

Screened

Senior Product and Systems Design Leader specializing in AI-enabled enterprise workflows

Charlotte, NC18y exp

“Former UX designer with 12 years in design who moved into product management and now leads complex AI-enabled retail experiences. Most notably, they championed Competitive Quote from an overlooked Hack Day prototype into a major initiative later valued at $300M over three years, combining strong product strategy, agentic UX thinking, and deep practical understanding of human-in-the-loop AI systems.”

“Full-stack product engineer who has built both operational systems and enterprise AI copilots in production. They owned an AI-powered inventory platform end-to-end, driving a 45% drop in stock issues, and also shipped a Microsoft Teams-based HR/IT copilot using RAG and workflow automation that reduced repetitive support queries by roughly 30%.”

“Built and owned Citigroup's ASTRA AI-powered test case generation platform end to end, from full-stack product experience to multi-agent LLM orchestration and RAG infrastructure. Drove test coverage from 40% to 95%, cut generation time from hours to minutes, and scaled the feature to 300+ daily users across 32 enterprise projects with sponsorship from Citi's CIO and Head of Engineering Excellence.”

“Built an internal AI-powered document search and Q&A platform at BNY that let employees query company documents in natural language and get grounded answers in seconds. Brings practical full-stack and LLM systems experience across React/TypeScript, FastAPI, Pinecone, OpenAI, and Claude, with clear emphasis on retrieval quality, hallucination reduction, and production monitoring.”

“Full-stack and AI engineer with Capital One experience spanning real-time customer dashboards and production fraud-analysis systems. They combine TypeScript/Next.js/Node.js product engineering with LangChain-based RAG architecture over a 400 GB credit-report corpus, delivering measurable impact including 35% lower frontend latency and 45% faster analyst workflows.”

“Built and deployed a compliance-sensitive LLM pipeline that extracts rebate logic from hospital–supplier medical contracts, using multi-layer redaction (regex/NER/dictionary), schema-validated structured outputs, and secure placeholder reinsertion. Hosted models on Amazon Bedrock to avoid retraining on sensitive data and improved both accuracy and cost by splitting the workflow into a lightweight section classifier plus a fine-tuned extraction model, orchestrated with LangChain and evaluated via layered, test-driven agent assessments.”

“Backend/platform engineer who owned a real-time customer analytics microservice stack in Python/FastAPI with Kafka streaming into PostgreSQL, including schema enforcement (Avro) and high-throughput optimizations. Strong Kubernetes + GitOps practitioner (EKS/GKE, Helm, Argo CD) who has handled CI/CD reliability issues with automated pre-deploy checks and rollbacks, and supported major migrations (on-prem to AWS; VM to EKS) with blue-green cutover planning.”

“Designed and deployed an enterprise LLM-powered clinical/pharmacy policy knowledge assistant at CVS Health, replacing manual searches across PDFs/Word/SharePoint with a HIPAA-compliant RAG system. Built end-to-end ingestion and orchestration (Airflow + Azure ML/Data Lake + vector index) with PHI masking, versioned re-embedding, and production monitoring (Prometheus/Grafana), and partnered closely with clinicians/compliance to ensure policy-grounded, auditable answers.”

“Built and deployed a production LLM-powered clinical note summarization system used by care managers to speed review of 5–20 page unstructured medical records. Implemented safety-focused validation (prompt constraints, rule-based and section-level checks, human-in-the-loop) to reduce hallucinations while maintaining low latency and meeting privacy/regulatory constraints, integrating via APIs into existing clinical tools.”

“Robotics software engineer who built a lightweight, ROS-free distributed control and telemetry stack for a Caltrans long-range culvert inspection robot. Strong in integrating heterogeneous hardware (UART motor controllers, Ethernet sensors, MJPEG cameras) and delivering real-time operator data via FastAPI/WebSockets, including reverse-engineering undocumented protocols and debugging network-induced latency with control-loop redesign.”

“Backend/API engineer with ~4 years experience building production services in .NET Core/PostgreSQL/Redis/Docker and optimizing real-world latency issues (claims ~60% response-time improvement). Also built and owned an end-to-end RAG-based AI assistant using Python/FastAPI, OpenAI APIs, and Pinecone, plus agentic workflows with reliability guardrails (retries, confidence thresholds, monitoring). Currently pursuing a master’s degree and targeting a $150k base salary.”

“Built and shipped a production LLM-powered agent that automated purchasing and inventory operations by integrating with live ERP data and returning structured, machine-readable outputs usable by downstream systems. Emphasizes real-world reliability through orchestration, strict schemas/validation, confidence-based fallbacks with human handoff, and monitoring/evaluation feedback loops to reduce silent failures and make issues observable.”