Vetted Retrieval-Augmented Generation Professionals

“Hands-on LLM/RAG engineer with production experience improving retrieval quality and stability by addressing messy data, vector DB inaccuracy, and top-K issues—ultimately redesigning to hybrid search with tuned keyword/semantic weighting and MCP-based data supplementation. Also brings strong AKS/Kubernetes deployment experience, optimizing CI/CD speed via lightweight local Docker validation and decomposing pods to avoid full rebuilds, plus a metrics-driven approach to agent/workflow testing and traceability.”

Rebecca Johnson

Screened ReferencesModerate rec.

Senior Product Manager specializing in AI workflows and healthcare SaaS

Remote, USA8y exp

“Homegrown product/program leader with 8 years of experience who has repeatedly found high-cost operational pain points and turned them into scalable product wins. Most notably, they built an address-validation and fraud-prevention system in non-emergency medical transportation that produced multi-million-dollar savings, and previously led an AI-assisted OCR workflow that raised accuracy to 98.6% and drove major efficiency gains.”

“AI Engineer with production experience building an LLM-powered conversational scheduling assistant (rules-based + OpenAI GPT agents) and improving responsiveness by ~40% through architecture optimization. Strong in orchestration (Airflow), containerized deployments, and data quality (Great Expectations/PySpark), with prior work automating population health reporting pipelines (Azure Data Factory → Snowflake) and delivering insights via Tableau to non-technical stakeholders.”

“Data scientist at Guardian Airwaves building a RAG-powered quiz generator using Grok AI, with hands-on experience solving hard document-ingestion problems (PDFs with images/tables) via unstructured.io and LlamaIndex. Has deployed production systems on AWS EC2 and brings a pragmatic approach to agent reliability (human-in-the-loop, LLM-based eval, latency/cost metrics) while effectively translating RAG concepts to non-technical stakeholders.”

“Built and shipped a production LLM-powered decision system that replaced a slow, inconsistent manual review process by turning messy text into structured, auditable outputs behind an API. Demonstrates strong end-to-end ownership of reliability and operations (schema validation, retries/fallbacks, latency/cost controls, monitoring for drift) and a disciplined approach to evaluation and regression testing. Experienced collaborating with non-technical reviewers to define success criteria and deliver interpretable outputs that get adopted.”

“AI/ML engineer with production experience building an enterprise network-fault prediction assistant that combines anomaly detection (Isolation Forest + LSTM) with an LLM layer for incident diagnosis and recommended resolutions. Hands-on with orchestration (Airflow, Prefect, Dagster) to run ETL/ELT and automated training/fine-tuning workflows, and has delivered AI solutions with non-technical stakeholders (retail customer support ticket categorization/response suggestions).”

“End-to-end engineer focused on AI-native enterprise systems, including a production generative knowledge platform using RAG + semantic search over internal documentation (React, Python/Flask, GPU-hosted NLP models, Pinecone) with strong CI/CD and observability. Reports concrete outcomes including 40% faster knowledge access and ~75% employee adoption, and has led incremental cloud-native modernization using feature flags, parallel runs, canary releases, and regression testing.”

“Backend-focused Python engineer who owned high-traffic internal services end-to-end (FastAPI/Django) including REST/GraphQL APIs, PostgreSQL optimization, async task processing via SQS, and full CI/CD. Strong Kubernetes-on-EKS and GitOps (ArgoCD + Helm) experience, plus Kafka real-time streaming work and phased cloud-to-on-prem migration support.”

Anjana Priya Swathi Samudrala

Screened

Junior Full-Stack AI Developer specializing in LLMs and RAG applications

Orlando, US2y exp

“Product-minded software engineer who owned a Shopify POS app end-to-end at Swym, shipping an MVP and then scaling iteration speed with E2E automation and CI/CD—resulting in a Shopify Badge, Top-5 App Store ranking, and +40% new user acquisition. Also built an ESG insights tool using React/TypeScript + FastAPI with Snowflake and a RAG pipeline, plus microservices patterns (async jobs, queues, DLQs, autoscaling) and internal Metabase/SQL analytics dashboards.”

Monthir Ali

Screened

Senior AI/ML Engineer specializing in LLMs, RAG, and VR/XR multimodal systems

Salt Lake City, UT8y exp

“PhD researcher (University of Utah) who built a production RAG-powered Virtual Reality Research Assistant to answer lab research questions with concrete citations. Implemented an end-to-end LangChain pipeline using PyPDFLoader, chunking strategies, OpenAI embeddings, and ChromaDB, with emphasis on grounding to reduce hallucinations and ensure research-grade accuracy. Collaborated closely with a non-technical PhD advisor to scope requirements, manage cost constraints, and demo iterative progress.”

Naisarg Halvadiya

Screened

Senior Full-Stack & AI Engineer specializing in scalable web platforms and LLM automation

Bengaluru, India4y exp

“Built a production agentic AI assistant in Python using Playwright plus Google Gemini’s vision capabilities to automatically document and execute UI workflows step-by-step, reducing developer time spent on trivial documentation/knowledge transfer. Also built an Apache Airflow ETL pipeline and has experience evaluating AI agents with human-in-the-loop methods, plus successfully communicated a vision-model-based CMS analytics PoC to non-technical university stakeholders and proposed it to Academic Technology with cost-savings rationale.”

“Healthcare-focused ML/AI engineer who has built clinical note summarization and medical image annotation solutions using LLMs, RAG, and multimodal models. They combine experimentation across major model providers with practical production concerns like monitoring, drift detection, and latency/cost tradeoffs, and also earned 2nd place in a Google hackathon for a medical AI assistant.”

“Backend/platform engineer with strong ownership of production systems, including a full Azure migration from a VM-based monolith to a containerized, event-driven microservices architecture. They combine cloud infrastructure, LLM/RAG optimization, and pragmatic stakeholder management, with measurable wins including 90% infra cost reduction, faster deployments, and significantly improved latency and token efficiency.”

“New grad candidate with graduate research experience building a multi-agent RAG pipeline from scratch, including worker-coach orchestration and an evaluation framework. Most notably, they improved structural similarity from 67% to 98% by designing validation and retry logic to reduce hallucinations, showing strong practical depth in agentic AI systems.”

“Full-stack and applied AI candidate who has shipped both a shift-management workflow product and an LLM-powered business insights system using Athena, S3, and Bedrock. They show strong grounding in prompt design, retrieval-based AI architecture, and practical human-in-the-loop product judgment, while also working in an early-stage university research project focused on accessibility for hard-of-hearing users.”

“Backend engineer with fintech/AI startup experience who built an Azure serverless, event-driven pipeline for large-scale crypto sentiment analysis and semantic search (OCR/NLP to vector search) and integrated LLM + blockchain data for predictive insights. Demonstrated measurable impact (25% lower retrieval latency, 10% fewer data errors, 15% higher engagement) and has led safe microservices migrations with strong security and reliability practices.”

“AI Engineer at Humanitarian AI who has built and productionized both a LangGraph-based multi-agent workflow system and a RAG pipeline (OpenAI embeddings + vector DB) with rigorous evaluation/guardrails. Reports strong measurable impact (60% faster workflow delivery, 40% fewer incidents, 70% reduced research time) and has prior enterprise modernization experience at Infosys migrating ETL to microservices with zero production incidents.”

“Built and deployed an agentic RAG platform at Centene Health to support healthcare claims and complaints workflows (Q&A for claims agents, executive complaint summarization, and compliance triage/classification). Experienced in LangChain/LangGraph orchestration, production deployment on AWS with FastAPI/Docker/Kubernetes, and implementing HIPAA-compliant guardrails to reduce hallucinations and ensure explainable outputs.”

“Built and deployed a scalable, production-ready LLM knowledge assistant using a RAG architecture (LangChain + vector store/FAISS) to replace keyword search for internal documents. Demonstrates hands-on expertise in hallucination reduction and retrieval quality improvements through semantic chunking, similarity tuning, prompt design, and human-in-the-loop validation, plus strong stakeholder communication via demos and visual explanations.”

“Built and productionized a clinical NLP + patient risk stratification platform at Dermanture, combining Spark/PySpark pipelines with BERT/BioBERT for entity extraction and text classification and downstream risk models in TensorFlow/scikit-learn. Experienced running regulated, auditable ML workflows with Airflow and AWS SageMaker, emphasizing data validation (Great Expectations), drift monitoring, and explainability (SHAP) to drive clinician trust and adoption.”

“Built a production "Mini RAG Assistant" for internal document Q&A, focusing on grounded answers (anti-hallucination), retrieval quality, and latency/cost optimization. Uses LangChain/LangGraph for orchestration and applies a metrics-driven evaluation loop (including reranking and semantic chunking improvements) while collaborating closely with product stakeholders.”

“Master’s program project lead who built and deployed a real-time sound recognition system (Flask + React Native + ML) that was adopted by 200+ university students. Demonstrates strong production engineering and cross-layer debugging—solving latency, unreliable uploads, and observability gaps using microservice separation, chunked/idempotent transfers, and packet-capture-driven network diagnosis—plus AWS/on-prem and IoT edge-to-cloud integration experience.”

“Accenture engineer who built and shipped a production RAG-based automation/chatbot for SAP incident triage and troubleshooting, embedding thousands of runbooks/logs/tickets into a semantic search pipeline and integrating it into Teams/Slack. Reported major productivity gains (30–60% time reduction), >90% validated answer accuracy, and sub-2-second responses, with strong orchestration (Airflow/Prefect/LangGraph) and reliability practices (guardrails, testing, monitoring).”