Vetted Retrieval-Augmented Generation Professionals

“Full-stack engineer with about 3 years of experience who is deeply hands-on with AI-assisted development and agentic systems. Built TubeAgent using LangChain, Ollama, FAISS, and Llama 3, and has demonstrated measurable impact by cutting review time by 90% and reducing deployment time from 30 minutes to under 5 minutes at NC State. Combines practical experimentation with strong architectural thinking around resilient, composable AI systems.”

Fadi Abbas

Screened ReferencesStrong rec.

Executive product leader specializing in AI-native products and EdTech platforms

Dearborn Heights, MI16y exp

“Product leader and founder with experience spanning EdTech, AI, LegalTech, and mobile imaging. He co-founded a tutoring platform that grew to 300K+ students and later built citation-grounded legal AI systems designed for high-trust, high-stakes workflows. Particularly compelling is his consistent philosophy of using AI to amplify human expertise rather than replace it, backed by global team leadership and strong product execution across EMEA, the US, and Asia.”

“Robotics software engineer who built a ROS Noetic-based perception-to-control stack for a pick-and-place robotic arm, integrating OpenCV/TensorFlow vision with motion planning and PID tuning. Demonstrated strong real-time debugging skills (rosbag, queue/latency fixes) and experience deploying reproducible robotics environments with Gazebo simulation, Docker, and GitLab CI.”

“AI/ML engineer with CVS Health experience deploying production LLM systems in regulated healthcare settings, including a large-scale RAG solution (1M+ documents) built for compliance-grade, auditable policy/regulatory Q&A with strong anti-hallucination controls. Also delivered an NLP summarization system for physician notes/case narratives by partnering closely with non-technical care operations stakeholders and iterating via prototypes, dashboards, and feedback loops.”

“Built and shipped a production LLM-powered grading platform that automates rubric-aligned scoring and feedback, with strong guardrails (RAG grounding, structured JSON, validation/retries) and operational rigor (metrics, drift monitoring). Experienced using CrewAI to orchestrate multi-agent workflows end-to-end and validating quality via gold-set benchmarking against human graders with regression testing on every prompt/model change.”

“Built and shipped production RAG/agentic systems in high-stakes domains (biomedical and legal), including an enterprise biomedical document retrieval platform over ~10k scientific docs and a multilingual African-law assistant at the World Bank. Deep hands-on experience with LangChain/LangGraph/LlamaIndex and evaluation tooling (LLM-as-a-judge, safety/hallucination detection), with measurable gains in retrieval quality and hallucination reduction.”

“Built a production SQL chatbot for access-log analytics that replaced manual custom report requests with natural-language querying, using LangGraph and a ChromaDB-backed RAG pipeline for grounded, consistent answers. Implemented a privacy-preserving design where the LLM never sees raw customer data (only query metadata) and has experience building multi-agent/tool-calling systems with LangGraph (DeepAgents), including solving sub-agent communication drift via self-reflection.”

“Built and deployed a production LLM-based RAG agent platform adopted by multiple business teams (Marketing, GTM, Recruiting, Customer Support) to automate knowledge search, Q&A, and content generation. Emphasizes production-grade reliability (grounding/validation/guardrails), rigorous evaluation/monitoring, and cost-aware scaling via model tiering, prompt/retrieval optimization, and caching using LangChain/LangGraph orchestration.”

“Built an LLM-powered academic research assistant for a professor (LangChain + OpenAI + arXiv) focused on synthesizing papers quickly, with emphasis on reliability (ReAct prompting, citation verification) and cost control (caching). Has production MLOps/orchestration experience at Cisco and HCL Tech using Kubernetes, plus MLflow and GitHub Actions for lifecycle management and CI/CD.”

“ML/NLP practitioner who built a retrieval-augmented generation (RAG) system for large financial and operational document sets using Sentence-Transformers (all-mpnet-base-v2) and a vector DB (e.g., Pinecone), with a strong focus on retrieval evaluation and chunking strategy optimization. Experienced in entity resolution (rules + embedding similarity with type-specific thresholds) and in productionizing scalable Python data workflows using Airflow/Dagster and Spark.”

“AI/ML Engineer who built a production RAG-based LLM system for insurance policy documents, turning thousands of messy PDFs into a searchable index using LangChain, Azure AI Search vectors, hybrid retrieval, and FastAPI. Strong focus on evaluation (MRR/precision@k/recall@k, REGAS) and performance optimization (vLLM), with prior clinical NLP experience using BERT-based NER validated on ground-truth datasets.”

“University hackathon finalist (2nd place) who built CareerSpark, a production-style multi-agent career guidance app in 24 hours using a hierarchical debate architecture with a moderator/judge agent. Has startup internship experience at LiveSpheres AI using LangChain for multi-LLM orchestration, and demonstrates a structured approach to testing/evaluation (golden sets, integration sims, latency/accuracy KPIs) plus strong non-technical stakeholder communication.”

“Built a secure, on-prem/private GPT assistant to replace manual SharePoint-style search across thousands of policies/SOPs/engineering docs, using a production RAG stack (LangChain/LangGraph, FAISS/Chroma, PyMuPDF+OCR, vLLM). Implemented layout-aware ingestion (including table-to-JSON) and a multi-agent retrieval/generation/verification workflow with strong observability and compliance guardrails, delivering ~70% reduction in search time.”

“Recent J&J intern who built a conversational RAG agent and led a shift from a monolithic model to a modular RAG workflow, cutting response time from several days to under a second by tackling data fragmentation, context retention, and embedding/latency optimization. Also worked on a large (7B-parameter) multimodal VQA pipeline for healthcare research and stays current via NeurIPS/ICLR and open-source contributions.”

“ML/AI practitioner with hands-on experience deploying models to production and optimizing for low-latency inference using pruning/quantization, with deployments on AWS SageMaker and Azure ML. Has orchestrated end-to-end ML pipelines with Airflow and Kubeflow (ingestion through evaluation) and emphasizes reproducibility via containerization and version-controlled artifacts, while effectively partnering with non-technical stakeholders using dashboards and business-aligned metrics.”

“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).”

“Built and deployed an end-to-end product that brings a research-paper approach into production for large-scale time-series clustering, with attention to partitioning, latency, and scalability. Also designed a Python-based backend validation service (comparing outputs to database ground truths) and handled production reliability issues by reproducing dataset-specific crashes and hardening corner-case behavior with client-friendly errors.”

“Serial entrepreneur since leaving corporate in 2009, working largely for equity on multiple startups. Building (1) academically rigorous, anti-overfitting quant/backtesting tools for retail investors (with potential applicability to smaller hedge funds lacking quant staff) and (2) a partner-led “social-as-a-service” platform for verticals like real estate/PropTech (including FSBO use cases) focused on first-party data capture vs. big tech.”

Chandan Chalumuri

Screened

Mid-level Data Scientist specializing in ML, NLP, and Generative AI

Tempe, AZ4y exp

“Data engineering / ML practitioner with experience at MetLife building transformer-based sentiment analysis over large unstructured datasets and productionizing pipelines with Airflow/PySpark/Hadoop (reported 52% efficiency gain). Also implemented embedding-based semantic search using Pinecone/Weaviate to improve retrieval relevance and enable RAG for customer support and document matching use cases.”

Apurva Banka

Screened

Mid-level Full-Stack & AI Engineer specializing in cloud, data platforms, and LLM automation

Houston, TX5y exp

“Software engineer/product builder who has owned an agentic affiliate lead-gen platform end-to-end (Django + React/TypeScript) and deployed it on Kubernetes in anticipation of 10x user growth from ~5K DAUs. Also has healthcare claims microservices experience using Kafka, including hands-on performance tuning to address consumer lag and broker pressure, and built an internal downtime alerting tool adopted across the organization.”