Vetted OpenAI API Professionals

silin liu

Screened

Mid-level AI/ML Engineer specializing in LLM agents, RAG, and enterprise ML systems

New York City, NY5y exp

“Built a production multi-agent recommendation/RAG system for internal data analysts to speed up weekly report creation by improving document discovery and automating report/SQL generation. Implemented LangGraph-based orchestration with deterministic agent routing, robust error handling (interrupt/resume), and metadata-driven semantic chunking for diverse PDF/document formats, plus monitoring for latency, throughput, and token/cost efficiency.”

“Built and shipped a production LLM-powered “Vet agent” that automates pet symptom intake across multimodal inputs (images/files/text/speech) and provides analysis/home-care guidance, reaching thousands of daily active users within two months. Demonstrates strong agent engineering fundamentals: state-machine orchestration with structured JSON, tool/schema validation, high-availability routing/failover, and rigorous offline/online evaluation loops with trace-driven reliability improvements.”

“Software engineer with experience spanning an SEL internship and Walmart, combining backend/data pipeline work (Python, Kafka, relational DBs) with DevOps practices (Docker, Grafana, GitHub/Jenkins CI/CD, GitOps). Notably contributed to a REST-to-GraphQL migration aimed at reducing cloud utilization and implemented testing strategies to validate the transition.”

“Built and deployed an AI-powered insurance claims fraud platform end-to-end using Java/Spring Boot, Kafka, OpenAI, pgvector, and AWS EKS. Stands out for combining LLM/RAG architecture with production-grade scalability and observability, delivering measurable impact including 62% less manual review, 40% better fraud precision, 37% higher throughput, and 99.95% uptime.”

Neeshma Narahari

Screened

Mid-level Software Developer specializing in backend microservices and cloud platforms

Irving, TX6y exp

“Full-stack product engineer with strong React and TypeScript depth who has owned dashboard features end-to-end, from UI architecture and rendering optimization through Spring Boot APIs and database query tuning. Particularly compelling for startup or high-growth teams: they’ve shipped 0→1 internal operations platforms, prioritized MVP workflows effectively, and iterated post-launch using user feedback, logs, and usage metrics.”

“Backend engineer with hands-on experience building event-driven Java/Spring Boot and Kafka systems, plus AI-assisted document-classification workflows in enterprise environments. Stands out for a thoughtful, risk-aware approach to AI: uses it to accelerate delivery, but emphasizes validation layers, confidence thresholds, observability, and human review before AI can affect downstream business actions.”

“Player-coach engineering leader currently running a Solution Architecture/FDE team responsible for both presales and postsales delivery. Stands out for combining enterprise systems thinking with hands-on AI product work: they built configurable tooling that sped delivery by ~30%, drove a Kafka-to-Pulsar architecture shift for scale, and spent the last two years building LLM-based document extraction and RAG inference pipelines shaped directly by user feedback.”

“Frontend engineering leader who owned the modernization of Everlane's large-scale e-commerce experience, migrating from a legacy stack to Next.js/Apollo/Cloudflare Workers while keeping a business-critical site running for nearly 1 million daily users. Stands out for combining architecture, browser performance, and conversion-focused execution—measuring success through Core Web Vitals, funnel improvements, and developer velocity.”

“Frontend engineer with JP Morgan Chase experience building data-heavy React/TypeScript products, including an AI-powered enterprise search application and workforce analytics dashboards. Stands out for combining reusable component architecture, Redux-driven state flow, responsive CSS, and production performance tuning for large-scale internal enterprise tools.”

Javon Lee

Screened

Senior Software Engineer specializing in AI platforms and cloud-native systems

Baltimore, MD8y exp

“Engineer with startup CTO experience and recent hands-on full-stack work at Microsoft and Clarity, focused on compliance and AML workflow platforms for financial services. Stands out for building scalable data and audit systems that reduced manual processing and improved performance, while operating effectively in ambiguous early-stage environments.”

“Amplitude contractor focused on AI/ML product development and backend systems, with hands-on experience shipping and improving LangChain-based event classification workflows in production. They combine LLM pipeline design, AWS data infrastructure, and pragmatic human-in-the-loop controls to make analytics systems faster, more reliable, and scalable.”

“Backend engineer with Citigroup experience who built and evolved a self-service user provisioning/identity backend, cutting onboarding from 45 minutes to under 2 minutes. Demonstrates strong production-grade integration and reliability practices (isolated integrations, retries, rollback logic, heavy logging) plus secure API development in Python/FastAPI with OAuth scope-based authorization and incremental, low-risk rollout strategies.”

“Backend engineer who built a Logistics-as-a-Service platform in Go, proactively refactoring a monolithic REST service into gRPC microservices to improve performance and maintainability. Led a 3-person team with disciplined code reviews, Dockerized DB migrations, and a canary-style rollout (5% traffic) monitored for latency and failures; also implemented JWT/OAuth2 RBAC and production-minded edge-case handling in an ordering system.”

“Built and productionized an autonomous research agent (AutoGPT) in a Docker/Kubernetes environment with Pinecone-based long-term memory and custom Python tools for analysis, visualization, and report drafting. Implemented layered guardrails (prompt templates, automated validation, self-critique loops, and monitoring) and achieved ~25% reduction in manual report generation time while scaling the workflow to support multiple concurrent users.”

“AI/ML engineer with HP experience building and productionizing an LLM-powered document intelligence platform (LangChain + Pinecone) to deliver semantic search and contextual Q&A across millions of enterprise support documents. Demonstrates strong MLOps and scaling expertise (Airflow, Kubernetes autoscaling, Triton GPU inference, monitoring with Prometheus/W&B) plus a structured approach to evaluation (A/B tests, shadow deployments, failover) and effective collaboration with non-technical stakeholders.”

“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.”

“Built and deployed a secure, production LLM-based document summarization and risk-highlighting tool for financial auditors, running inside a private Azure environment to protect confidential data. Focused on reliability (hallucination mitigation via retrieval-based prompts and source citations) and validated performance through comparisons to auditor summaries plus a user pilot, cutting review time by about half.”

“Machine learning/NLP engineer who built a production-oriented retrieval-based AI system at Morgan Stanley for healthcare use cases, combining RAG over unstructured patient records with deep-learning medical image segmentation (U-Net/Mask R-CNN). Strong in end-to-end pipelines and MLOps (Spark/MongoDB, AWS SageMaker, CI/CD, monitoring, automated retraining) and in entity resolution/data quality validation for noisy clinical data.”

Dhyey Desai

Screened

Intern AI/ML Engineer specializing in RAG, multimodal AI, and LLM systems

Los Angeles, California0y exp

“Built and shipped 'PetPulse,' a production AI pet-health note system that records voice notes, transcribes them, converts transcripts into structured symptom/event data, and supports grounded Q&A over a user’s notes and vet PDFs. Demonstrates full-stack LLM product execution (FastAPI + GPT-4 + Firebase), with concrete reliability/performance work (async endpoints, caching, RAG/embeddings, function calling) and user-centered iteration with a non-technical product stakeholder.”

Utkarsh Srivastava

Screened

Junior Machine Learning Engineer specializing in LLMs, RAG, and medical imaging

New York City, USA3y exp

“At Fileread, the candidate built and deployed an LLM-powered legal document classification and retrieval layer for an agentic extraction system that turns unstructured legal PDFs into structured tables with line-level citations. They productionized a RAG-style pipeline (ingestion, embeddings, retrieval, reranking, generation) and report 95%+ F1 across 70+ legal categories, emphasizing rigorous evaluation and close collaboration with legal domain experts for high-stakes precision.”

Sai Charan Kolla

Screened

Mid-level AI/ML Engineer specializing in LLMs, RAG, and MLOps on AWS

TX, USA5y exp

“LLM engineer who built a production document intelligence/RAG pipeline to extract structured data from thousands of unstructured PDFs, cutting manual review time by 60%. Experienced with LangChain and Airflow orchestration plus rigorous evaluation (labeled datasets, prompt testing, HITL review, monitoring) to improve accuracy and reduce hallucinations while partnering closely with non-technical operations stakeholders.”

“Built and shipped a production-grade agentic RAG system at CVS Health for patient adherence and medication recommendations, processing 20k+ patient records/day. Strong focus on real-world reliability: hybrid retrieval tuned with re-ranking (<400ms latency), strict JSON/schema validation and tool guardrails, and monitoring/drift detection that reduced MTTD from 6 days to 18 hours while improving recommendation accuracy (+8%) and cutting escalations (~23%).”