Vetted Retrieval-Augmented Generation (RAG) Professionals

“Hands-on backend/AI engineer who solo-built two production Claude-based agent systems: an internal Slack RAG over Confluence/Jira/code/regulatory docs and a HIPAA/GDPR-compliant patient chatbot with embedding guardrails and expert-in-the-loop evals. Also architected a multi-region patient portal + microservices platform with Terraform/CI-CD and federated gateways, delivering major onboarding automation and strong reliability wins (PgBouncer, chaos/perf testing).”

“Backend/AI engineer from an early-stage Japan-based startup (WorkAI) who built a multi-tenant RAG system integrating Notion/Slack/Google Drive with Pinecone and OpenAI, including a chatbot retrieval workflow. Experienced in production reliability (rate limits, retries, verification layers), strong Python/FastAPI engineering practices, and PostgreSQL performance optimization; currently based in India and needs sponsorship.”

“Full-stack engineer who shipped a production "Financial Insight" assistant dashboard in Next.js App Router/TypeScript, integrating a RAG pipeline (embeddings + ChromaDB + LLM) via route handlers and owning post-launch performance (latency, token cost, retrieval relevance). Also built/optimized Postgres-backed workflows for an outbound dialer and callback routing engine handling ~10,000 daily contacts, validating query performance with EXPLAIN (ANALYZE, BUFFERS).”

“ML/NLP engineer with recent Scotiabank experience building production-grade indexing automation over large-scale emails and customer databases, combining LLM fine-tuning (Mistral, XLM-R) with fuzzy matching to exceed 95% accuracy under strict banking constraints. Also built a RAG-based chat agent using Gecko embeddings, Vertex AI Search, Gemini, and cross-encoder reranking, and delivered a text-to-SQL chatbot at SOTI through iterative fine-tuning and benchmark-driven experimentation.”

“Software engineer who built and launched an end-to-end Ad Scheduler that automated campaign creation across Google Ads and Meta using Azure Functions/Service Bus, PostgreSQL, and a React frontend—reducing manual marketing ops work. Also shipped a production internal RAG chatbot leveraging a data warehouse + Cube semantic layer, Gemini embeddings, vector search, and Claude, with Langfuse tracing and brand-based access controls; work was cut short due to layoffs.”

“Full-stack engineer who built a cloud storage app feature (file upload/management) with Next.js App Router + TypeScript and owned post-launch improvements. Also has internship experience building a geospatial AI chatbot: designed Postgres/PostGIS data models and optimized spatial queries, and implemented an LLM workflow orchestrated with LangChain/LangGraph plus a RAG pipeline grounded in OpenStreetMap data to reduce hallucinations.”

“Robotics software/ML engineer who built perception and navigation-related ML systems for autonomous supermarket carts, including object detection, shelf recognition, and obstacle avoidance. Strong ROS/ROS2 practitioner who optimized real-time performance (reported 50% latency reduction) and deployed containerized ROS/ML pipelines at scale using Docker, Kubernetes, and CI/CD.”

“Backend/data platform engineer who owned end-to-end production services for a fleet analytics/GenAI platform, spanning FastAPI microservices on Kubernetes and AWS (EKS + Lambda) event-driven workloads. Strong in reliability/observability (OpenTelemetry, circuit breakers, idempotency), data pipelines (Glue/Airflow/Snowflake), and measurable performance/cost wins (SQL 10s to <800ms P95; ~30% compute cost reduction).”

“GenAI engineer who has deployed production LLM/RAG chatbots for internal document search, focusing on reliability (hallucination reduction via prompt guardrails + retrieval filtering) and performance (latency improvements via caching). Experienced with LangChain/LangGraph orchestration for multi-step agent workflows and iterates using monitoring/logs and benchmark-driven evaluation while partnering closely with product and business teams.”

“Software engineer with experience across data engineering and backend/platform work: owned a Databricks/PySpark real-time pipeline powering customer dashboards with a 15-minute SLA, and helped modernize an investor web app from JSP to React/TypeScript with API + SQL/materialized-view performance improvements. Also contributed to breaking a Java monolith into microservices (Redis + gRPC on AWS EKS) and built an EC2-deployed Play Store/App Store crawler that reduced third-party data costs.”

“GenAI/ML engineer with production experience at Cognizant and Ally Financial, building end-to-end LLM/RAG systems and ML pipelines. Delivered a domain chatbot trained from 90k tickets and 45k docs, improving intent accuracy (65%→83%), scaling to 800+ concurrent users with 99.2% uptime and sub-150ms latency, and driving +14% customer satisfaction. Strong in Azure ML + DevOps CI/CD, Dockerized deployments, and explainable/PII-safe modeling using SHAP/LIME to satisfy stakeholder trust and GDPR needs.”

“Robotics software engineer who built the software layer for an autonomous warehouse sorting system, spanning navigation/path planning, task scheduling, and backend services. Deep hands-on ROS 2 Foxy experience (Nav2/costmaps) and real-time multi-robot debugging, using simulation-driven analysis plus incremental/partial re-planning to handle dynamic obstacles in production-like warehouse environments.”

“JavaScript/React performance-focused engineer who contributed upstream to an open-source virtualization/pagination library, fixing overlapping-fetch race conditions and introducing prefetch/deduping patterns that cut load times from ~3s to <900ms and reduced render thrash ~35%. Also built healthcare automation systems (clinical summary and claims triage), including a FastAPI + RAG pipeline that retrieved CPT/ICD evidence, improving decision accuracy from 67% to 86% and reducing turnaround time by 40%.”

“Built and productionized Azure-based LLM/RAG systems for regulatory/compliance use cases, including automating analyst research and compliance report generation across large unstructured document sets. Demonstrates strong practical depth in hallucination mitigation, hybrid retrieval tuning (BM25 + embeddings), and production MLOps (Databricks, Cognitive Search, AKS, Airflow/MLflow), plus proven ability to deliver auditable, explainable solutions with non-technical compliance teams.”

“ML/NLP engineer focused on real-time IT ops analytics, building a predictive maintenance/anomaly detection platform end-to-end (multi-source ETL, streaming, modeling, and production deployment on GCP/Vertex AI). Uses deep learning (LSTMs, autoencoders/VAEs) plus embeddings (SentenceBERT) and vector search to improve incident correlation and search, citing ~40% reduction in duplicate alert noise.”

“Backend-leaning full-stack engineer who ships AI-enabled products end-to-end: built CodeChat, a production internal codebase Q&A tool using RAG with Pinecone and a model-agnostic wrapper across OpenAI/Anthropic/AWS Bedrock, cutting AWS costs ~50% and latency ~45%. Also built and operated RealityStream, a Flask-based real-time forecasting API with JWT/RBAC, MLflow model versioning, and Prometheus/Grafana observability, including handling a real production latency incident via rollback, preloading, and caching.”

“Senior data scientist with ~5 years’ experience building production ML/NLP systems in finance (Wells Fargo) and deep learning for sensor analytics in connected vehicles (Medtronic). Has delivered end-to-end platforms combining time-series forecasting with transformer-based NLP, including automated drift monitoring/retraining (MLflow + Airflow) and standardized Docker/CI/CD deployments; achieved a reported 22% precision improvement after domain fine-tuning.”

“Engineer with Deloitte experience building real-time analytics products and scalable Kafka/Go/Postgres pipelines, plus production LLM features using RAG and embeddings. Demonstrates strong focus on performance, reliability, and guardrails/evaluation loops to reduce hallucinations and improve real-world AI system quality.”

“Backend/full-stack engineer from Foxconn Industrial Internet who led development of a production TypeScript/Node.js facility monitoring platform delivering near real-time manufacturing metrics (e.g., downtime and OEE) using MySQL + InfluxDB and a React dashboard. Demonstrates strong production operations mindset with queue-based workers, idempotency/DLQ patterns, structured observability, and automated Docker + GitLab CI/CD deployments.”

“Built and launched a personalized sprint-planning dashboard to reduce recurring planning friction, choosing a simple, reliable scoring approach over a complex model. Iterated based on team feedback (more control, dependency clarity, performance), achieving a reported 20% drop in task spillovers; transparent about not yet shipping production LLM/RAG features but actively learning.”

“Full-stack engineer with production experience across React/TypeScript, Node/Express, and Java/Spring Boot, operating containerized systems on AWS (EKS/ECS/EC2/RDS/S3) with strong observability (CloudWatch/Grafana). Notable for fixing a real checkout/order-placement failure end-to-end by adding frontend submission guards and backend idempotency with Redis + Kafka deduplication, then validating impact via technical metrics and business KPIs. Has also built Kafka-based integrations/pipelines with robust retry/backfill/reconciliation patterns in retail and banking contexts.”

“Built and scaled an AI-powered voice/chat patient engagement platform at Penn Medicine from early prototype into production clinical workflows, focusing on latency, edge cases, and user trust. Strong in LLM reliability engineering (structured prompts, validation/fallbacks), real-time troubleshooting with observability, and cross-functional enablement through pilots, demos, and sales/customer partnership.”

“Founding member of Tausight, building AI systems to detect and protect PHI for healthcare organizations; helped take the company through post–Series A funding and exited after ~6 years. Drove a strategic collaboration with Intel’s OpenVINO team—becoming the first to deploy it in a real production system and improving model performance by ~30% on customer Intel-CPU machines.”

“Software engineer/product owner who has led end-to-end delivery of AI and content-management platforms, including building RAG-based reliability improvements and migrating fragile systems to containerized AWS ECS/Kubernetes with Terraform-managed CI/CD. Experienced designing event-driven microservices (SQS/SNS/RabbitMQ), scaling queue consumers with autoscaling, and creating internal Python tooling to standardize data connectors (e.g., BigQuery/Airtable/internal APIs) to speed iteration.”