Vetted Retrieval-Augmented Generation 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.”

“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.”

“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%.”

“Unity mixed-reality developer who shipped ZenPlay, a multiplayer Go app on Meta Quest, integrating a C# rules engine with XR input, Meta avatars, Hathora-hosted matches, and Vivox voice chat (reported ~700 MAU). Also built a production LLM agents backend (LangChain + RAG with Pinecone/ChromaDB + ChatGPT) powering embodied conversational avatars, with a strong focus on streaming voice latency optimization (ElevenLabs TTS) and cross-platform WebXR delivery (Quest/iOS/Android).”

“Backend/AI engineer with deep healthcare experience building production Python microservices that turn raw clinical audio into structured notes and insights. They owned systems end-to-end across architecture, launch, monitoring, and incident response, with measurable impact including 40% lower operating costs, 22% better latency, and 99.9% uptime in a regulated environment.”

“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 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.”

“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.”

“Backend/DevOps-leaning engineer who has owned a Python serverless platform on AWS (Lambda, DynamoDB, Step Functions), including complex multi-step business workflows with transaction-based consistency and robust failure handling. Also supported an on-prem SQL to Azure Data Lake migration by building and monitoring Python + Azure Data Factory ETL pipelines, and led GitOps-style CI/CD automation with GitHub Actions (tests, security scans, automated deployments).”

“Built and productionized an AI-assisted merchant onboarding automation workflow for Kort Payments, replacing slow manual underwriting document review with structured extraction, cross-document validation, and human-in-the-loop guardrails. Emphasizes reliability via scenario-based testing, repeatability checks, and deep observability (timestamped logs), plus incremental rollout with legacy fallback to prevent regressions.”

“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.”

Emmanuel Eruck

Screened

Senior Full-Stack Software Engineer specializing in AI and FinTech

Toronto, Canada8y exp

“Frontend engineer who led the mentorAi SaaS platform UI end-to-end at IBL.ai, building real-time React/Redux experiences backed by WebSockets and scaling quality with Playwright E2E tests in GitHub CI. Also worked at Paymentology for ~2 years on fintech features (token management, Visa card creation/assignment and funding flows), modernizing an existing React codebase by introducing TypeScript and strengthening CI/coverage with SonarQube to reduce deployment bugs.”

Thota Rajkumar

Screened

Junior Cloud & AI Infrastructure Engineer specializing in Agentic AI and AWS

San Jose, CA2y exp

“Built and deployed a production AI career-advice agent designed to combat unreliable/generic LLM guidance by grounding outputs in retrieval-first RAG over resumes/job/hiring data, with multi-step reasoning, structured memory, and evidence-only prompting to reduce hallucinations. Implemented the system with LangChain/Python and deployed on AWS as scalable microservices orchestrated via REST and asynchronous calls, iterating closely with career coaches and students.”

HarshaVardhanRao Vemuganti

Screened

Junior AI/ML Engineer specializing in Generative and Agentic AI

Lafayette, Louisiana4y exp

“Built and deployed a production-grade LLM agent for credit management and accounts receivable automation, integrating ERP/MySQL data via a RAG pipeline and exposing services through FastAPI with Pydantic-validated outputs on AWS Bedrock. Emphasizes reliability and compliance for financial operations using schema validation and human-in-the-loop review, reporting ~32% reduction in manual work and ~41% improvement in response time/reliability.”

Kishan Kumar Reddy Konreddy

Screened

Junior Software Engineer specializing in distributed systems and cloud platforms

2y exp

“Software engineer (Lance Soft Engineering) who built a Java/gRPC real-time request tracking system supporting ~20K simultaneous requests, using Kafka event streaming and PostgreSQL to improve transparency and cut support requests by 35%. Demonstrates strong production operations skills—resolved live latency spikes with Kafka async messaging (+48% throughput) and executed safe migrations using parallel runs, staging validation, and blue-green deployments.”

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.”