Vetted Retrieval-Augmented Generation (RAG) Professionals

“At CVS Health, the candidate productionized a RAG-based LLM solution in a regulated healthcare setting, emphasizing reliable data pipelines, LoRA fine-tuning, monitoring, safety guardrails, and A/B testing. They have hands-on experience troubleshooting real-time RAG failures (e.g., chunking/embedding issues) and regularly lead developer-focused demos/workshops while translating technical architecture into business value for stakeholders.”

“Built and productionized an AI NL-to-SQL capability inside legacy accounts receivable software (React + Spring Boot + Postgres/pgvector RAG), adding semantic caching and a SELECT-only validation layer to satisfy infosec. Achieved measurable impact (3 days to seconds turnaround, 60% token cost reduction, 50% latency reduction) with strong adoption (40 analysts, 50+ queries/week) and documented/monitored via Confluence + logging and user feedback loops.”

“Research Assistant at the University of Houston who built and live-deployed a production RAG system for 1000+ research documents, using hybrid retrieval (dense+BM25+RRF) with cross-encoder reranking and RAGAS-based evaluation; reported 66% MRR, 0.85+ faithfulness, and 68% lower LLM inference costs. Also built a deployed LangGraph multi-agent research system (Researcher/Critic/Writer) with tool integrations (Tavily, arXiv) and dual memory (ChromaDB + Neo4j), plus freelance automation work delivering a WhatsApp chatbot and n8n workflows for a wholesale clothing business.”

“Built and deployed a live production LLM document Q&A platform (DocumindAI) with an adaptive RAG pipeline (Claude + Cohere embeddings + pgvector), source-cited structured outputs, and engineered fallbacks for reliability and sub-2s latency. Also has enterprise integration experience at Tech Mahindra working with messy IFS ERP XML integrations, using validation/normalization and JTA transactions to prevent partial writes and data corruption.”

Ishaan Umesh Mandliya

Screened

Mid-Level Full-Stack Software Engineer specializing in AI/ML and cloud-native systems

Los Angeles, CA3y exp

“At BondiTech, built and deployed customer-facing backend improvements for enterprise dashboards handling 1M+ records, redesigning a .NET/Entity Framework API with server-side pagination/filtering and feature-flagged rollout to cut latency from ~15s to ~2s. Experienced integrating customer systems into existing APIs, including stabilizing a legacy CRM sync by normalizing inconsistent IDs, handling strict rate limits with batching, and adding DLQs plus reconciliation reporting.”

“Accenture consultant who shipped an LLM-based production solution during a client cloud migration to parse application code and identify only the database objects actually used, cutting migration time by 30% and accelerating realization of cloud cost benefits. Emphasizes production robustness with timeouts/retries/fallback routing, validation, observability, and a disciplined eval/monitoring loop that turns failures into regression tests.”

Laasya Muktevi

Screened

Intern Machine Learning Engineer specializing in forecasting, NLP, and RAG systems

San Jose, CA5y exp

“Intern who built and deployed a production LLM-powered contract analysis system for finance teams: Azure Document Intelligence for text/table extraction plus Gemini prompting to surface key terms and risks via an async API and simple UI. Emphasizes reliability in production with fallbacks, guardrails against hallucinations, and operational concerns like latency/cost/versioning, delivering summaries in under 30 seconds instead of hours.”

Krishna Madani

Screened

Mid-Level Full-Stack Software Developer specializing in cloud-native web applications

New York City, NY4y exp

“Capgemini engineer with hands-on ownership of production TypeScript backend integrations and loyalty-platform modernization. Built AWS event-driven microservices (SNS/SQS/Lambda) with GraphQL vendor calls and DynamoDB persistence, emphasizing reliability patterns like retries and idempotency; reports ~25% response-time improvement after migrating/optimizing services and workflows.”

Michael Chaves

Screened

Senior Creative Technologist & Full-Stack UX Engineer specializing in Generative AI and XR

Los Altos, CA12y exp

“Design engineer/product designer who built an end-to-end creator + review/moderation system for a UGC platform, spanning automated checks, human QA, final review, and creator feedback. Comfortable working directly with HTML/CSS/TypeScript and component systems, using prototyping and field observation to reduce reviewer hesitation, improve consistency, and prevent creator errors upstream.”

Rayyan Alam

Screened

Junior Robotics & Machine Learning Engineer specializing in autonomy and RAG systems

Arlington, VA1y exp

“New-grad robotics software engineer with hands-on ROS 2 autonomy experience (Nav2, SLAM Toolbox, AMCL) and a strong track record debugging real-world instability (QoS, lifecycle timing, sensor dropouts). Built an HRI speech system on a Stretch 3 robot with deterministic, context-aware templates to manipulate trust/competence/emotion conditions, and integrated an LLM high-level planner that outputs PDDL for classical task planning and replanning.”

Aishwarya Thorat

Screened

Intern Data Scientist specializing in ML engineering and LLM agentic workflows

San Francisco, CA6y exp

“Built an agentic, multi-step LLM system that generates full-stack code for API integrations using LangChain orchestration, Pinecone/SentenceBERT RAG, and a human-in-the-loop feedback loop for iterative code refinement. Also collaborated with non-technical content writers and PMs during a Contentstack internship to deliver a Slack-based AI workflow that generates and brand-checks articles with one-click approvals.”

“Analytics-focused candidate with experience building SQL/Python pipelines and dashboards for donor, campaign, and website performance reporting. They have worked with messy multi-source data, standardized metric definitions, and delivered automated reporting that reportedly reduced manual effort by about 80%.”

“ML/AI engineer with hands-on ownership of production recommendation and RAG systems at Northern Trust. They combine transformer modeling, latency optimization, cloud deployment, and monitoring with measurable business impact, including 14% accuracy gains, 12% engagement improvement, and 19% better query relevance.”

“Healthcare ML/AI engineer at Cigna who has owned a clinical RAG pipeline from prototype through production, monitoring, compliance, and iteration. Stands out for combining LLM product delivery with healthcare-grade safety and explainability, driving a 38% retrieval precision gain, 42% hallucination reduction, and meaningful improvements in team velocity and system reliability.”

Sree Damineni

Screened

Mid AI/ML Engineer specializing in financial and insurance analytics

USA3y exp

“Senior AI/ML engineer focused on production ML, LLMs, and MLOps, with concrete experience shipping fraud detection and enterprise RAG systems. They combine strong deployment and monitoring discipline with measurable business impact, including 31% precision improvement in fraud detection and 37% better answer relevance in a financial-document QA system.”

“Built end-to-end ML and GenAI systems at Northern Trust, including a production RAG-based document intelligence platform for financial reports and contracts. Stands out for combining strong MLOps execution with practical product judgment—improving forecast accuracy by 22%, document review accuracy by 38%, and cutting deployment time by 45% while keeping latency and reliability production-ready.”

“ML/AI engineer with strong production ownership across predictive ML and Generative AI systems. They’ve delivered measurable business impact through real-time churn/drop-off prediction, RAG-based document QA, and scalable LLM optimization, with a consistent focus on reliability, safety, latency, and developer productivity.”

Praveen LAKSHMAN

Screened

Mid-level Software Engineer specializing in backend systems and workflow automation

Birmingham, AL4y exp

“Early-career AI engineer currently pursuing a Master's, with hands-on experience building and improving RAG pipelines using LangChain. They stand out for moving beyond naive retrieval into multi-step retrieval and feedback-loop designs to reduce hallucinations, and are now exploring multi-agent systems with distinct retrieval, coding, and validation roles.”

“Built production AI systems for Macy's and Bloomingdale's, including an embeddings-based pipeline to clean trending search queries and an end-to-end 'Ask Macy's' multi-agent chat experience. Brings hands-on experience with real-world agent orchestration, tool integration, quality evaluation, and business-facing safeguards in a large-scale e-commerce environment.”

“Backend/platform engineer with experience across Cigna, Cognizant, and a university environment, focused on reliability, distributed systems, and regulated-domain workflows. Stands out for combining Kubernetes/Kafka/AWS infrastructure expertise with a production RAG-based healthcare compliance assistant that cut manual reporting work from 30-45 minutes to under 2 minutes while maintaining strong uptime and data-quality controls.”

Aniket Dhanawade

Screened

Mid-level Full-Stack Engineer specializing in cloud-native and AI-powered applications

USA3y exp

“Candidate has a thoughtful, hands-on approach to AI-assisted software development, treating AI as a pair programmer while retaining ownership of architecture, tradeoffs, and final code quality. They have practical experience using multi-agent workflows to ship small features end-to-end, including planning, execution, and gap detection under human oversight.”

“Software engineer who recently shipped an authentication and role-based access feature for a web app, using AI selectively for boilerplate, debugging, and test suggestions while retaining ownership of architecture, security, testing, and final review. Stands out for a disciplined, security-first approach to AI-assisted development and a pragmatic preference for lightweight API-driven solutions over unnecessary framework complexity.”

“Full-stack engineer with experience spanning AI-powered product features and healthcare fraud detection systems. Has built end-to-end LLM-enabled applications, customer-facing recommendation systems at scale, and operational platforms that improved real-time investigations and flagged over 1,200 high-risk cases quarterly.”

“Front-end engineer with hands-on ownership of a React/TypeScript workforce management platform used by site managers and field workers in the energy sector. Stands out for building scalable, reusable UI architecture for complex task/checklist workflows while also improving real-world usability and performance through pagination, bulk actions, and close feedback loops with operational users.”