Vetted Retrieval-Augmented Generation (RAG) Professionals

“Built and deployed an enterprise GenAI knowledge assistant over thousands of internal PDFs/reports using a RAG stack (GPT-4 + Hugging Face embeddings + vector DB) to reduce manual search and SME escalations. Uses LangGraph/LangChain to orchestrate modular agent workflows with relevance filtering and fallback handling, and applies rigorous evaluation (golden datasets, edge cases, A/B tests) with production monitoring metrics.”

“Interned at Zonda where he built an AI-driven semantic search solution over ~280M housing/builder records. Iterated from local LLMs via llama.cpp quantization to a vector-embedding retrieval system, then boosted semantic accuracy with a custom spaCy NER layer and re-ranking, optimizing for latency through precomputation. Collaborated with economics-focused stakeholders to reduce manual document/paperwork time by enabling natural-language search over internal data.”

“Built an LLM multi-agent “ingredient safety” analyzer for cosmetics that cuts consumer research time from ~20+ minutes to minutes, using LangGraph orchestration, hybrid retrieval (Qdrant + Tavily), and safety-focused critic validation (false rejections reduced ~30%→~8%). Also has research-internship experience building computer-vision pipelines to classify emerald color/clarity by translating gem-expert heuristics into quantitative model features.”

“Full-stack engineer with 3+ years using Java/Spring Boot (Citi) and React, who built a production observability dashboard monitoring 53 microservices across 17 clusters with real-time health/latency tracing and significant performance improvements (cut load time from ~10s). Also designed a serverless AWS face-recognition system (Lambda/S3/SQS) built to handle burst traffic (~1000 concurrent requests), demonstrating strength in scalable, event-driven architectures.”

“GenAI Engineer at Infosys who built and deployed a production multi-agent RAG system for a top-tier bank, scaling to ~50,000 queries/day with 99.9% uptime. Drove measurable gains (45% accuracy improvement, 30% API cost reduction) through open-source LLM fine-tuning, Pinecone indexing/retrieval optimization, and AWS-based MLOps/monitoring, and has experience enabling adoption via developer workshops and customer-facing collaboration.”

“Researcher from the University of South Dakota who built a production medical RAG system to help interpret model predictions by retrieving relevant clinical notes and medical literature, overcoming retrieval accuracy and imaging-dataset challenges through semantic chunking and metadata-driven indexing. Also has hands-on orchestration experience with Airflow and Azure Data Factory, plus a pragmatic approach to LLM evaluation and stakeholder-driven iteration.”

“Siemens AI engineer who shipped production multi-agent LLM systems across cybersecurity and sustainability, including a vulnerability automation agent that cut manual work 70%. Deep in orchestration (LangGraph supervisor-worker state machines), reliability engineering (async fault tolerance, retries, spike handling), and rigorous evaluation (offline benchmarks, LLM-as-a-Judge improving label agreement 28.9%) with measurable production guardrails.”

“AI/ML engineer who has shipped production AI systems end-to-end, including an automated multi-channel (Gmail/WhatsApp/voice) candidate interviewing workflow and an enterprise RAG knowledge search platform. Demonstrates strong production rigor (monitoring, A/B tests, guardrails, schema validation, shadow testing) with quantified impact: ~60–70% reduction in interview evaluation time and ~20–30% relevance gains in RAG retrieval.”

“Healthcare GenAI engineer who built a HIPAA-compliant, auditable RAG-based claims decision support system at Molina Healthcare, processing 3M claims and delivering major impact (48% faster manual reviews, 43% higher decision accuracy). Deep hands-on experience with LangChain orchestration, vector search (ChromaDB/FAISS), embedding fine-tuning, and safety controls (confidence scoring, rule validation, human-in-the-loop escalation) for clinical workflows.”

“Financial-services AI engineer who shipped a production investment research assistant using RAG over internal research reports, SEC filings, and meeting transcripts, with a strong emphasis on truthfulness and guardrails. Built a structured evaluation loop (200+ golden test cases, RAG Triad metrics) that directly improved retrieval quality (e.g., fixing year-mismatch retrieval, boosting sensitive-query performance by 18% and cutting hallucinations to near zero) and scaled ingestion to ~10k messy documents with RabbitMQ + OpenTelemetry.”

Monish Sri Sai Devineni

Screened

Mid-level Machine Learning Engineer specializing in financial AI, NLP, and MLOps

Boca Raton, FL5y exp

“AI/ML engineer with experience at Accenture and Morgan Stanley, building production LLM systems (GPT-3 summarization) and finance-focused ML models (credit risk and trading anomaly detection). Combines MLOps depth (Docker/Kubernetes, AWS SageMaker/Glue/Lambda, MLflow, A/B testing, drift monitoring) with practical domain adaptation techniques like few-shot prompting and RAG/knowledge-base integration.”

Junhui Huang

Screened

Intern Machine Learning Engineer specializing in LLMs, MLOps, and NLP

Providence, RI1y exp

“Built and deployed a production LLM-driven Dungeons & Dragons game where the model acts as a dungeon master, adding a structured combat system and a macro-state tree to ensure campaigns converge to a clear ending. Fine-tuned Gemini 2.5 Flash on Vertex AI and deployed on GCP with Kubernetes, using RAG over DnD rules/spells plus multi-agent orchestration (intent-based routing between narrative and combat agents) to reduce hallucinations and improve reliability.”

Vaibhav Sharma

Screened

Mid-level Software Engineer specializing in AI/ML and data platforms

Remote, USA5y exp

“AI/ML engineer who built a production agentic system to automate computational research experiments (simulation execution, parameter exploration, and numerical analysis) and mitigated context-window failures using constrained tool-calling/prompt-chaining patterns in LangChain with OpenAI tool-enabled models. Also has adtech/big-data pipeline experience at InMobi, orchestrating Spark jobs in Airflow to filter bot-like user IDs and publish clean IDs to an online NoSQL store for live serving, plus Apache open-source collaboration experience.”

Yun-Ting Chiou

Screened

Junior Full-Stack Software Engineer specializing in TypeScript, React, and Java microservices

Chicago, IL2y exp

“Software engineer with finance-domain experience who built an internal transaction management system end-to-end at Prospect Equities (TypeScript/React Native + Java Spring Boot microservices on AWS), delivering 40% lower query latency and 73% operational efficiency gains. Has also designed Terraform-provisioned, SQS-based distributed systems and scaled workloads to 10,000+ concurrent users, including monolith-to-SOA modernization that cut internal review time by 47%.”

Akshit Modi

Screened

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

Remote, USA5y exp

“Healthcare/clinical ML practitioner who built and productionized ClinicalBERT-based pipelines to extract and standardize oncology EHR data, improving downstream model F1 from 0.81 to 0.92 while controlling training cost via LoRA/QLoRA. Experienced orchestrating real-time AWS ETL/ML workflows (Glue, Lambda, SageMaker) and partnering with clinicians using SHAP-based interpretability, contributing to an 18% reduction in readmissions and full adoption.”

Aditya Jaiswal

Screened

Intern Software Engineer specializing in cloud, DevOps, and applied AI

Carlsbad, CA1y exp

“Full-stack engineer with startup ownership experience (Aiir) building 15+ TypeScript/Go microservice APIs on GCP Cloud Run with Kafka-based async event streaming and React CRM integrations for billing/analytics. Strong post-launch operator who tuned Oracle performance (partitioning/indexing/query optimization) and validated a 23% retrieval-time reduction via AWR, and has a quality/DevSecOps mindset (94% Pytest coverage, GitHub Actions, SonarQube, Twistlock, CloudWatch) including migrating 18+ production CI/CD pipelines.”

Suloni Praveen

Screened

Entry-Level Software Engineer specializing in data engineering and ML systems

Los Angeles, CA0y exp

“Built an end-to-end Next.js/TypeScript LLM-based scientific PDF analyzer using local Ollama/Llama inference to prioritize privacy and cost, producing structured research artifacts (e.g., authors/methods/findings) with ~92% extraction accuracy. At Qualtrics, helped replace a batch pipeline with a real-time, low-latency ML inference service (Python/Go on Kubernetes) using Redis caching, Grafana-based observability, and graceful fallbacks to protect UX during failures.”

“Analytics-focused candidate with hands-on experience using SQL and Python to clean messy business data, automate reporting, and build practical customer analytics solutions. Notable examples include a 70% reduction in reporting time through Python-based Excel automation at Shell and stakeholder-friendly retention/RFM segmentation work for small business clients in freight and winery contexts.”

Atharva Bhide

Screened

Entry Software Engineer specializing in AI/ML and multimodal systems

Los Angeles, CA1y exp

“Built and shipped a production healthcare AI platform for a clinic in Brea, LA that combined LLM-based clinical report generation, voice agents for appointment workflows, and camera-based patient monitoring. Stands out for pairing multimodal AI architecture with production-grade reliability and compliance practices, while delivering concrete business results including 90% workflow automation, 200 hours saved per month, and a 60% improvement in customer retention.”

“Product-minded full-stack engineer with deep experience building React/TypeScript + serverless/SQL systems and improving both operational reliability and user activation. They stand out for connecting low-level architecture decisions like idempotency and atomic updates with business outcomes such as reduced support burden and lower 30-day cancellations, while also designing configurable multi-tenant product systems with strong guardrails.”

“Early-career analytics candidate with hands-on experience in SQL/Python data pipelines, Tableau reporting, and marketing engagement analytics across internship and startup settings. Stands out for combining rigorous data quality practices with practical AI system design, including an end-to-end GPT-4 grading capstone that emphasized explainability and human oversight.”

“Built and owned Alight's AI-powered Search Summary feature end-to-end, using a RAG pipeline with OpenSearch and Bedrock, and drove a 20% increase in user feedback scores. Stands out for bringing rigorous production evaluation to LLM systems via live LLM-as-a-judge monitoring, and for experience with advanced agentic architectures, hybrid search, and reranking at scale.”

Darshi Jain

Screened

Mid-level Customer Success Manager specializing in ads, product strategy, and analytics

San Francisco, CA4y exp

“Revenue-focused seller with experience at Amazon and Vedanta, combining data-driven prospecting, account expansion, and GTM process building. Stands out for turning performance insights into repeatable growth motions—driving $3.1M annual revenue uplift and 40% format adoption at Amazon, while also building new-market playbooks from scratch in high-ambiguity industrial segments.”

Ramesh Namperumal

Screened

Executive technology leader specializing in AI/ML, data engineering, and enterprise architecture

Alpharetta, GA27y exp

“Technical founder building an AI IT helpdesk agent startup, currently leading product development as acting CTO/CPO and doing much of the development personally with a small partner group. Brings years of cross-industry technical experience, product/vendor evaluation expertise, and a deliberate strategy to delay outside capital until the product and customer traction are stronger.”