Vetted OpenAI API Professionals

“Built and shipped Site Audit AI, a production multi-turn Claude-based agent that autonomously crawls websites, calls tools, and generates scored audit reports—reducing a manual 2-3 hour developer workflow to under 60 seconds. Also brings practical experience integrating inconsistent payroll/HR data across platforms like QuickBooks and Keka, with a strong focus on validation, fault tolerance, and resumable workflows.”

“Backend/AI engineer who built an enterprise RAG chatbot over 40,000+ technical documents, owning the system from ingestion and retrieval design through launch, optimization, and incident prevention. Stands out for treating LLM reliability as a data, retrieval, and observability problem—delivering 90%+ benchmark accuracy, ~50% fewer hallucinations, and major gains in lookup speed and latency.”

“Built a production multi-agent RAG assistant using LangChain/LangGraph with OpenAI embeddings and FAISS, focusing on retrieval quality and latency (Redis caching, parallel retrieval, precomputed embeddings). Experienced orchestrating ETL/ML pipelines with Airflow and Databricks Workflows, and has delivered an AI assistant for business ops to extract insights from policy/compliance documents through close non-technical stakeholder collaboration.”

“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%.”

Ramya Jonnala

Screened

Principal/GenAI Engineer specializing in LLMs, RAG, and MLOps

Plano, TX9y exp

“Built a production AI-powered university marking system that automates question generation and grading from PDF course materials using a RAG pipeline (S3 + Pinecone) orchestrated with LangChain/LangGraph and deployed on AWS ECS via Docker/ECR and GitHub Actions CI/CD. Addressed a key real-world LLM challenge—grading consistency—by implementing rubric-based scoring, retrieval re-ranking, and standardized context summarization, validated against human instructors.”

Teja Puvvula

Screened

Senior Full-Stack Software Engineer specializing in web apps, cloud, and data integrations

Florida, USA3y exp

“Full-stack engineer with strong production ownership across frontend, backend, and cloud ops. Led an AdTech “Status Centre” initiative at Beautiful Code that automated DSP integrations (XML/SOAP/REST) and reduced manual work by 90%+, using an event-driven architecture with retries and OTEL/Datadog observability. Also built and hosted a MERN app (Onegrad), load-tested with k6, and has experience running large migrations (~8k users) with validation and alerting.”

ROHITH DAMARLA

Screened

Mid-level Backend Engineer specializing in high-scale systems and LLM pipelines

Syracuse, NY6y exp

“Open-source-focused TypeScript/JavaScript engineer who built a lightweight Node.js utility library to standardize LLM-agent message formatting, tool invocation, and safe schema-validated JSON outputs. Emphasizes composable abstractions, real-world performance profiling/benchmarks, and strong community feedback loops (GitHub issues, structured errors, logging hooks). Also did research at Syracuse University on converting natural language into structured JSON with validation layers.”

Tharun Chowdary Malepati

Screened

Mid-level AI/ML Engineer specializing in GenAI, NLP, and production MLOps

5y exp

“AI/LLM engineer who built and deployed a production healthcare RAG chatbot ("DoctorBot") with strict medical safety guardrails, an 85% confidence-gated verification layer, and latency optimizations that cut responses from ~8s to ~2–3s. Also worked on finflow.ai to generate finance/banking test cases from BRDs, collaborating closely with non-technical domain stakeholders, and has hands-on orchestration experience with LangChain/LangGraph and agentic evaluation/monitoring practices.”

“Analytics-focused candidate from SWAP PM with hands-on experience turning messy onboarding and user behavior data into reliable funnel and retention reporting using SQL and Python. They owned an end-to-end onboarding improvement project, aligned stakeholders on metric definitions, and helped drive changes that reduced onboarding time by about 45%.”

“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 a production-grade clinical and insurance document AI system in a HIPAA/PHI-regulated environment, taking it from experimentation through Azure deployment, monitoring, and iterative improvement. Stands out for translating RAG/LLM research into reliable microservices with strong safety controls, drift monitoring, and human-in-the-loop workflows that cut manual review time by 60-70%.”

“ML/AI engineer with hands-on experience building healthcare and fraud-detection systems from experimentation through deployment, monitoring, and retraining. Stands out for combining real-time IoT pipelines, cloud-native MLOps, and GenAI/RAG in regulated healthcare settings, with reported impact including reduced emergency response times and a 25% reduction in manual diagnosis time.”

“Unity/C# developer who has shipped multiple Steam titles and owned systems end-to-end, including a large-scale in-game automation feature (a configurable stock-bot) designed for performance with massive object counts. Also built an open-source Unity Editor CLI extension leveraging cloud/LLM-style code workflows, and has shipped multiplayer (Mirror) plus cross-platform VR (Meta Quest) and mobile (iOS/Android) applications, using Datadog for live issue monitoring.”