Vetted Retrieval-Augmented Generation (RAG) Professionals

“Full-stack engineer with startup-style ownership across backend, frontend, and AI systems, spanning Java/Spring, React, Node/TypeScript, and LLM-powered retrieval. Shipped a workspace intelligence layer using LangChain, OpenAI, and Pinecone to paying customers, while also improving core product metrics like workspace creation success (+30%), latency (450ms to 280ms), and deployment cycle time (-40%).”

“Built end-to-end AI products across fintech and healthcare, including a real-time loan risk prediction system and a patient feedback insights platform. Stands out for combining full-stack delivery, production ML/MLOps on AWS, and pragmatic human-in-the-loop safeguards; reported a 22% improvement in prediction accuracy.”

“Built both a fantasy sports analytics product and a privacy-sensitive AI assistant for therapists, showing range across consumer and healthcare use cases. Particularly notable for designing self-hosted, HIPAA-conscious LLM systems with RAG, structured outputs, observability, and human-in-the-loop guardrails for clinical workflows.”

“Product leader and founder/co-founder type who helped build AI products from concept through pilot, including Mira, an AI-powered tourism platform that reached 60K users and 12K engagements during a Tuscany pilot. He appears especially strong at translating between executives and technical/design teams, structuring cross-functional delivery, and applying human-centered AI principles in education through a RAG-based K-12 tutoring product, TUUTOR.”

“Senior full-stack engineer with startup experience building multi-tenant B2B SaaS platforms for manufacturing and financial operations. Strongest in Python back-end development and React/TypeScript front ends, with hands-on AWS microservices, enterprise integrations like Siemens, and measurable performance gains including a 30% reduction in application load times.”

“Frontend engineer with hands-on experience building complex, real-time React/TypeScript products, including an AI-powered document Q&A dashboard and a geospatial analytics platform. Stands out for measurable performance wins—cutting UI interaction latency from roughly 300-800ms to 20-50ms—and for scaling map-based visualizations to tens of thousands of live entities using Mapbox GL, Deck.gl, WebGL, Web Workers, and Redux Toolkit.”

“CoreAI intern at The Home Depot who improved the Magic Apron Assistant by building a production video ingestion + RAG retrieval system for long videos (uploads and YouTube), including a graph-based retrieval module to speed up and improve relevance. Experienced with Kubernetes orchestration (HPA) and production reliability practices like caching, monitoring, regression testing, and stakeholder-driven requirements.”

“Built a production LLM-RAG system at McKesson to let internal healthcare operations teams query large volumes of unstructured operational documents via natural language with source-backed answers, designed with HIPAA/FHIR compliance in mind. Demonstrated strong production engineering across hallucination mitigation, retrieval quality tuning, and latency/scalability optimization, using LangChain/LangGraph and Airflow plus rigorous evaluation/monitoring practices.”

“Built and shipped a production agentic LLM analytics platform that lets non-SQL business users query relational databases in plain English via a RAG + LangChain/LangGraph workflow and FastAPI service. Emphasizes safety and reliability with guardrails (validation/access control), testing/evaluation frameworks, and performance optimization (caching, monitoring, Dockerized scalable deployment), reducing dependency on data teams and speeding analytics turnaround.”

“Software/ML engineer who built a production automated job-finding and cold-email personalization system for Fortune 500 outreach, using JobSpy for dynamic scraping, LangChain orchestration, and LLM+vector DB semantic search with grounding/relevance metrics and guardrails. Also delivered a predictive investment analytics platform for financial advisors, communicating results via Tableau dashboards and portfolio KPIs like Sharpe ratio and drawdowns.”

Pooja Miryala

Screened

Mid-level AI/ML Engineer specializing in NLP, LLMs, and RAG for banking and healthcare

Ohio, USA4y exp

“Deployed a real-time LLM-driven call center summarization and agent-assist platform at Fifth Third Bank, combining transformer models (BERT/GPT) with FastAPI inference on AKS and vector storage (ChromaDB/PostgreSQL). Emphasizes production-grade reliability (autoscaling, CI/CD, monitoring) and measurable evaluation (A/B testing), and translates model outputs into business-facing Power BI insights for call center leadership.”

Sai somapalli

Screened

Senior LLM Engineer specializing in Generative AI, RAG, and multimodal assistants

USA6y exp

“GenAI/NLP engineer with experience building classification and summarization pipelines in PyTorch and deploying multimodal GPT-4-style workflows. Has integrated LLM applications across OpenAI, Azure OpenAI, and Amazon Bedrock, and uses LangChain/LlamaIndex/Semantic Kernel to orchestrate RAG and agent workflows with production-focused evaluation metrics like task success rate and groundedness.”

Andrew Clayman

Screened

Senior Data Scientist specializing in ML, NLP, and production AI systems

Remote8y exp

“Machine learning/NLP engineer with deep Azure stack experience (Data Factory, Databricks/Spark, Delta Lake, Azure OpenAI, Azure AI Search) who built end-to-end production systems for semantic clustering, entity resolution, and hybrid search. Demonstrated measurable gains from embedding fine-tuning (~15% retrieval precision, ~10–12% nDCG@10) and designed scalable, quality-checked pipelines with MLOps best practices.”

Piyush Rajendra

Screened

Mid-level AI/ML Engineer specializing in production RAG systems and MLOps

Athens, GA4y exp

“Built and deployed a GPT-4 + Pinecone RAG system that lets users query large internal document collections with grounded, cited answers. Demonstrates strong applied LLM engineering (chunking experiments, hallucination controls, metadata recency boosting) plus production-minded evaluation/monitoring and performance tuning (rate-limit mitigation via pooling/batching). Also effective at translating complex AI concepts to non-technical stakeholders through prototypes and live demos, helping secure client sponsorship.”

Sreedivya Nagalli

Screened

Junior AI/ML Engineer specializing in deep learning and full-stack ML applications

2y exp

“Built and operated a production-used RAG-based AI study planner (GPT-4 + FAISS) that handled 250+ concurrent users, with real-world reliability engineering (caching, fallbacks, schema validation, Redis state, monitoring). Also has healthcare data integration experience at Medinet Analytics, standardizing messy EHR/practice-management data with canonical schemas, idempotency hashing, and compliance-grade audit trails.”

Sravya Chunduri

Screened

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

Virginia, USA4y exp

“AI/ML Engineer with 3+ years of experience spanning RAG pipelines, MLOps, large-scale data workflow automation, and resilient Playwright-based UI automation. At Black Hawk Network and Wipro, they describe shipping production systems with strong observability and compliance controls, including reducing flaky automation failures from 30% to under 2% and automating 3+ TB/day reconciliation workflows.”

Varun Sharma

Screened

Mid-level AI Builder and Data Engineer specializing in GenAI and data pipelines

Remote, USA4y exp

“Full-stack AI product engineer who personally built ViGenAir, a multimodal system that turns long-form video into ads using FastAPI, React, and agentic scoring. Stands out for handling complex 50GB+ media pipelines, re-architecting systems to eliminate OOM failures, and making opaque AI workflows usable through interactive visual UX that improved trust, speed, and retention.”

“Backend engineer with hands-on ownership of a production POS platform, including architecture, CI/CD, Kubernetes deployment, and live incident handling. Also built a RAG-based document Q&A system using OpenAI/Anthropic with hybrid retrieval, evaluation metrics, and fallback logic, showing both traditional backend depth and practical applied AI experience.”

“Backend/data engineer focused on production Python and AWS: built FastAPI REST services and a containerized ECS Fargate + Lambda architecture deployed via Terraform/CI-CD. Strong in data engineering (Glue/S3/Parquet/RDS) and operational reliability (CloudWatch/SNS, retries, schema-evolution handling), with experience modernizing legacy SAS reporting into Python microservices using feature flags and parity validation.”

“Full-stack/AI engineer who has shipped production systems spanning real-time analytics dashboards and an internal LLM-powered knowledge assistant. Experienced with RAG pipelines (embeddings/vector DB, semantic retrieval, query rewriting) plus evaluation loops and guardrails, and builds observable Kafka-based data pipelines monitored with Prometheus/Grafana.”

“Full-stack/AI product engineer who has shipped both a production-style React finance app and multiple LLM-powered systems end-to-end. Particularly strong in turning early-stage AI concepts into production workflows, including a Bedrock-based multi-turn chatbot with durable session memory and a medical credentialing document parser that cut pipeline failures by 50%+ on large, messy real-world files.”

“Frontend engineer with 3 years of professional experience and a Master's degree who has built a React/TypeScript interface for a two-sided marketplace with role-based dashboards and Stripe escrow flows. Stands out for combining security-conscious UI architecture, measurable browser performance optimization, and polished workflow design for demanding users across desktop and mobile.”

“Senior product leader who helped transform Submittable from a single-program grant tool into a multi-program impact platform, driving ARR from $20M to $70M+ while improving retention and margins. Particularly strong in enterprise platform strategy and human-centered AI, with a clear philosophy of using AI to augment expert judgment rather than replace it.”

“Built and shipped a production LLM-powered agent for supply chain operations that integrates ERP data and automates multi-step decision-making with tool calling, state management, and structured JSON outputs. Emphasizes production reliability (guardrails, fallbacks, monitoring, idempotency) and reports strong business impact: 40% faster decisions, 30% higher throughput, and 25% efficiency gains.”