Vetted Retrieval-Augmented Generation (RAG) Professionals

“New grad who shipped an LLM-powered writing app (“Write-it”) to production on Azure with CI/CD (GitHub Actions + JFrog) and implemented an unconventional RAG pipeline to prevent repetitive prompts using embeddings and cosine similarity. Also participated in a Luma AI image/video generation hackathon, iterating with artist feedback and improving usability by rewriting non-technical prompts via an LLM.”

“Built and shipped "OnCall Copilot," a production Slack-based RAG assistant that answers on-call questions from runbooks and postmortems with citations using a FAISS vector index. Emphasizes reliability and measurable performance via strict guardrails ("no evidence, no answer"), evaluation metrics, drift monitoring, and operational hardening with Docker, logging, health checks, and offline fallback.”

“Built and deployed a "personal second brain" product (CloneMind) with an end-to-end RAG pipeline for retrieving information across PDFs, URLs, images, and audio using Next.js/Node.js/Postgres/Supabase/Redis. Demonstrates strong practical depth in retrieval quality tuning, latency reduction via caching, and stateful orchestration with LangChain/LangGraph, plus experience persuading a non-technical professor stakeholder by shipping a working prototype.”

“Graduate-school lab engineer who built and owned the final architecture of a Microservices Hub that integrates REST APIs, issues API keys, monitors 10+ Linux servers, and visualizes service dependencies via a topology graph. Strong in bridging legacy and modern stacks (Dockerized and non-Dockerized services like Apache/screen) using deep Linux/networking knowledge, plus practical real-time audio streaming for STT/TTS and experience mentoring others.”

“Backend Python engineer who owned the full backend build of an AI-driven platform for UK golf clubs, including FastAPI microservices, vector search, and a tuned LangChain+Pinecone RAG pipeline focused on cost and hallucination reduction. Experienced deploying Django/FastAPI/Flask stacks on AWS-backed Kubernetes with GitOps/ArgoCD-style delivery, plus executing legacy-to-AWS migrations and building Kafka-based real-time analytics pipelines.”

“Built and productionized an LLM-powered customer support system using a RAG architecture with structured document ingestion, embedding retrieval, and prompt templates for product-specific grounding. Experienced diagnosing live agent/workflow failures (e.g., retrieval regressions after new docs) by refactoring ingestion/chunking and adding grounding constraints plus evaluation benchmarks. Also supports go-to-market by joining discovery calls, shaping MVP workflows into demos/prototypes, and creating post-launch documentation to drive adoption.”

“Full-stack engineer who shipped and owned a production Document Chat feature built with Next.js App Router/TypeScript and a Node/Express RAG backend, including JWT-secured route handlers and streaming responses. Demonstrated strong post-launch ownership by improving latency (~30%) via MongoDB indexing/query optimization and reducing AI costs through caching, backed by profiling with React Profiler and Chrome DevTools.”

“Software engineer (internship experience) who built and owned an AWS serverless multi-user “challenge” feature end-to-end (UI + REST APIs + DynamoDB + deployment), delivering measurable gains in latency (-30%), debugging time (-50%), and join drop-offs (~-30%). Also productionized a multilingual RAG-based QA system with vector retrieval and guardrails, improving accuracy to ~85% and driving ~20% DAU growth.”

“Built and shipped a production LLM-powered incident response agent for a microservices platform, automating alert triage and safe remediation recommendations with strong guardrails (RAG grounding, structured JSON outputs, rule-based validation, and human-in-the-loop). Implemented state-machine orchestration (Redis/Kafka), comprehensive eval/monitoring, and an error categorization pipeline that cut hallucination errors ~40% and reduced MTTR ~30%.”

CharanKumar Pathakamuri

Screened

Entry-Level GenAI/LLM Engineer specializing in agentic systems and RAG

Baltimore, MD1y exp

“LLM/AI agent engineer with consulting/contract experience (Kanhaiya Consulting LLC) who deployed a production AI agent to automate BIM list workflows end-to-end—from database understanding and data cleaning to automated visualizations/dashboards. Worked around restricted real-time data access by generating synthetic data and improving outputs via supervised fine-tuning, and uses AWS-based LLMOps observability (Opic/OPEC) plus hybrid retrieval (vector+BM25 with reranking) to optimize relevance, latency, and cost.”

Vishnu Priyan Sellam Shanmugavel

Screened

Mid-Level Applied AI Engineer specializing in LLM services, RAG, and OCR/NLP extraction

Arlington, VA4y exp

“Backend/platform engineer who built and evolved a large-scale healthcare document processing system (OCR + LLM orchestration) in Python/FastAPI on Google Cloud (Cloud Run, GCS, Firestore), processing ~1.5M files per batch and tens of millions overall. Emphasizes reliability and operational safety via deterministic IDs, idempotent state machines, strong observability, and self-healing reconciliation, plus disciplined migrations using dual-run validation and incremental rollouts.”

Revanth P

Screened

Mid-level DevOps Engineer specializing in AWS, Azure, Kubernetes, and GenAI infrastructure

Walnut Creek, CA4y exp

“Database/platform engineer with stronger hands-on experience in AWS and Azure than GCP, but able to speak credibly about cloud database architecture, automation, and reliability engineering. They led an on-prem MySQL to RDS/DynamoDB migration, built Terraform/Python-based zero-touch database operations, and described a performance incident where latency dropped from 2s to under 300ms while supporting 2x traffic.”

“Built and owned a production RAG-based internal knowledge assistant end-to-end, from experimentation through cloud deployment and monitoring. Demonstrated strong practical GenAI judgment by choosing prompt optimization and retrieval tuning over fine-tuning for dynamic data, driving a 40% to 50% reduction in time to answer while improving relevance, lowering hallucinations, and increasing productivity.”

“Built an end-to-end agentic population health strategy copilot for healthcare leadership, turning broad chronic disease questions into structured, evidence-backed strategy briefs. Stands out for combining healthcare domain knowledge with production-grade GenAI implementation, including LangGraph orchestration, Databricks/MLflow deployment, human review, and quality gates focused on citations, metrics, risks, and safety.”

“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.”

“Backend engineer (Encore) who led the evaluation and redesign of a high-volume, low-latency real-time retrieval/ranking and inference platform on AWS, shifting from tightly coupled services to a modular architecture for better fault isolation and independent scaling. Strong focus on production reliability, observability, and security (JWT/RBAC, multi-tenant scoping, Postgres/Supabase RLS), with disciplined migration playbooks (feature flags, shadow traffic, dual writes/reconciliation).”

“Built production LLM/agent systems for procurement and contract spend controls, including a proactive contract value leakage detection platform that moved an organization from reactive audits to pre-payment rejection. Combines multi-agent orchestration (Semantic Kernel/LangChain/AutoGen), document AI benchmarking (Textract vs Azure DI), and MLOps/testing (MLflow, QTest/Pytest) with strong security practices (RAG-grounded responses to prevent prompt injection). Integrated anomaly alerts directly into SAP SES workflows and Power BI dashboards, citing ~$38M leakage addressed across large spend environments.”

“Frontend engineer with experience across university and product companies (University of Montreal, Dopely, Takhfifan), owning React/TypeScript features end-to-end. Notably built a mathematically complex, multi-mode color wheel UI for designers and led quality practices at scale via conventions, RTL testing, and code reviews for junior developers, plus performance and reusability improvements in existing codebases.”

“Built and deployed production LLM applications including a natural-language-to-read-only-SQL system focused on ambiguity handling and query safety (schema whitelisting, intent validation, confidence checks, deterministic execution). Experienced with LangChain-based, modular agent orchestration and RAG document QA for large PDFs, with a metrics-driven testing/evaluation approach and cross-functional delivery with marketing on an AI content recommendation/search tool.”

“Product-minded full-stack engineer with hospitality tech experience who owned and scaled a multi-region guest verification/check-in workflow (ID/passport scanning, OCR, and government submissions) and built internal tools that cut manual entry up to 80%. Also built a React/TypeScript + FastAPI RAG “second brain” with async ingestion workers and an event-driven e-folio email microservice hardened with idempotency and retries.”

“Built and deployed a production AI-powered personalized learning platform (Django + FastAPI) featuring an LLM+RAG tutoring assistant and automated grading. Demonstrates strong applied LLM reliability engineering (structured JSON outputs with Pydantic validation, hallucination control via FAISS-based RAG thresholds and refusals) plus scalable async microservice design and Airflow-orchestrated ETL across AWS/GCP.”

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.”