Vetted Vector Search Professionals

Vladimir Novick

Screened ReferencesStrong rec.

Executive CTO and Software Architect specializing in AI systems and cloud platforms

Israel, Israel22y exp

“Startup-minded technical founder currently running Novicklabs and building Itervox.dev, an AI agent orchestration platform for developer teams. Previously served as CTO at EventLoop and shows strong insight into multi-agent tooling, observability, security, and the open-source-to-cloud path for developer infrastructure products.”

“Data scientist at Guardian Airwaves building a RAG-powered quiz generator using Grok AI, with hands-on experience solving hard document-ingestion problems (PDFs with images/tables) via unstructured.io and LlamaIndex. Has deployed production systems on AWS EC2 and brings a pragmatic approach to agent reliability (human-in-the-loop, LLM-based eval, latency/cost metrics) while effectively translating RAG concepts to non-technical stakeholders.”

“BI/analytics candidate with healthcare and product analytics experience spanning Honor Health and ASU. They’ve worked on messy multi-system hospital supply data and also owned analytics for an AI-powered tax assistant, with quantified outcomes including 97% faster search, 92% retrieval accuracy, 30% fewer ad hoc procurement requests, and 15% lower operational cost.”

“Hands-on backend engineer with practical experience improving latency in Django-based API systems by fixing missing indexes and eliminating N+1 queries. Also built an AI scheduling system using FastAPI, a relational database, AI/ML workflows, and an operational reporting dashboard, with a clear bias toward correctness and maintainable architecture.”

“Senior AI/ML engineer with hands-on experience building production LLM systems in healthcare, including RAG-based clinical question answering and end-to-end MLOps on Vertex AI and Kubernetes. They combine strong platform engineering with applied GenAI work, citing a 35% improvement in factual accuracy and a 30% boost in internal team productivity through modular Python services and CI/CD.”

“Built and launched a production AI knowledge assistant at Virtusa used by 8,000 people, combining RAG, tool use, and strong reliability practices to cut lookup time by 60%. Also owns full-stack delivery, including a real-time transaction monitoring dashboard built with React, Spring Boot, and Kafka handling 200K API requests per day.”

“Backend/platform engineer with strong ownership of production systems, including a full Azure migration from a VM-based monolith to a containerized, event-driven microservices architecture. They combine cloud infrastructure, LLM/RAG optimization, and pragmatic stakeholder management, with measurable wins including 90% infra cost reduction, faster deployments, and significantly improved latency and token efficiency.”

“AI engineer focused on production-grade LLM systems rather than prompt-only solutions, with hands-on experience building citation-grounded RAG products and multi-agent workflows. Most notably built a financial document intelligence system for SEC filings and contracts that achieved ~92% recall@5, cut latency below 2 seconds, reduced hallucinations, and turned analyst research from hours into seconds.”

“Backend engineer with fintech/AI startup experience who built an Azure serverless, event-driven pipeline for large-scale crypto sentiment analysis and semantic search (OCR/NLP to vector search) and integrated LLM + blockchain data for predictive insights. Demonstrated measurable impact (25% lower retrieval latency, 10% fewer data errors, 15% higher engagement) and has led safe microservices migrations with strong security and reliability practices.”

“AI Engineer at Humanitarian AI who has built and productionized both a LangGraph-based multi-agent workflow system and a RAG pipeline (OpenAI embeddings + vector DB) with rigorous evaluation/guardrails. Reports strong measurable impact (60% faster workflow delivery, 40% fewer incidents, 70% reduced research time) and has prior enterprise modernization experience at Infosys migrating ETL to microservices with zero production incidents.”

prashanth Jamalapurapu

Screened

Mid-level AI/ML Engineer specializing in data engineering, LLM/RAG pipelines, and recommender systems

5y exp

“Research assistant at St. Louis University who built and deployed a production document-intelligence RAG system (Python/TensorFlow, vector DB, FastAPI) on AWS, focusing on grounding to reduce hallucinations and latency optimization via caching/async/batching. Also developed a personalized recommendation system for the Frenzy social platform and partnered closely with product/UX to define metrics and iterate on hybrid recommenders and cold-start handling.”

Jaykumar Kotiya

Screened

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

Boston, MA6y exp

“Built and deployed production LLM systems for summarizing sensitive legal and financial documents, emphasizing GDPR-aligned privacy controls and scalable hybrid cloud architecture. Experienced with Kubernetes/Airflow orchestration and rigorous testing/monitoring practices, and has delivered measurable business impact (18% conversion lift) by translating AI outputs for non-technical marketing stakeholders.”

Abhishek Ingle

Screened

Junior Full-Stack & AI Software Engineer specializing in React/Next.js and LLM systems

Bloomington, IN2y exp

“Backend engineer with hands-on experience building low-latency, high-concurrency real-time chat on AWS (Node.js/Socket.IO/MongoDB) and improving reliability under unstable networks, contributing to ~40% user adoption growth. Also built FastAPI-based AI assistant context retrieval (RAG) APIs with embeddings/vector search, and has strong production experience in rate-limit handling, async refactors with safe rollout, and Supabase Auth/RLS optimization.”

Kingsley Torlowei

Screened

Senior Software Engineer specializing in AI systems and data platforms

Remote8y exp

“Built and productionized LLM agents that ingest multi-source workplace data (Slack, meetings, calendars, PM tools) to extract entities (tasks/decisions/risks/initiatives) and generate customer insights like risk alerts, deadline-miss prediction with evidence, and workload overload detection. Also architected a graph-DB-backed multi-step agent using LangChain + Pydantic with async queue/worker execution and LLM-as-judge evaluation plus human review loops.”

“ML engineer with hands-on experience building banking AI systems end-to-end, including a customer-targeting model that improved campaign response rates by about 10%. Also shipped a RAG-based banking FAQ/support feature with safety guardrails and production optimizations around retrieval quality, latency, and cost, plus reusable Python services that reduced duplicate work for other engineers.”

Meghana Divve

Screened

Mid-level Full-Stack Software Engineer specializing in cloud-native enterprise applications

Tampa, FL6y exp

“Built and launched a production internal AI support assistant at CompuCom, focused on reducing time spent searching across systems by combining retrieval, internal tool use, and grounded LLM responses. Stands out for pragmatic zero-to-one execution: scoped the product in phases, prioritized safety over premature autonomy, and iterated using real user feedback to improve relevance, usability, latency, and cost.”

“Built a Personal Finance Copilot, a full-stack AI assistant for transaction search, spending analysis, subscription tracking, and grounded financial Q&A, with multi-step tool-calling orchestration and hybrid retrieval/memory architecture. Stands out for using AI coding agents aggressively to accelerate planning and implementation while maintaining strong ownership of system design, testing, security, and reliability.”

Raghava Sammeta

Screened

Mid-level Full-Stack Engineer specializing in cloud, microservices, and AI systems

Atlanta, GA4y exp

“Built and owned Destination Together, a collaborative travel platform, end-to-end across frontend, backend, data, infrastructure, and payments. Stands out for combining React/Node microservices, PostgreSQL concurrency design, real-time messaging, Dockerized deployment, and Gemini-powered route-aware travel suggestions in a single product.”

“Built a production LLM/RAG document extraction and game/quiz content workflow using LLaMA 2, LangChain/LangGraph, and FAISS, achieving ~94% accuracy and reducing turnaround from hours to minutes. Demonstrates strong applied MLOps/orchestration (CI/CD, MLflow, Databricks/PySpark), robust handling of noisy/variable document layouts (layout chunking + OCR fallbacks), and practical reliability practices (human-in-the-loop routing, drift monitoring, A/B testing).”

“AI/LLM engineer who has shipped production RAG chatbots using LangChain/OpenAI with FAISS and FastAPI, focusing on real-world constraints like context windows, concurrency, and latency (reported ~40% latency reduction and <2s average response). Experienced orchestrating AI pipelines with Celery and fault-tolerant long-running workflows with Temporal, and has applied NLP model tradeoff testing (Word2Vec vs BERT) to drive measurable accuracy gains.”

“Built and productionized an agentic RAG assistant using Ollama + LangChain + MCP + ChromaDB to speed up and standardize access to operational knowledge from tickets and runbooks. Focused on real-world reliability: mitigated timeouts/latency with retries and concurrency limits, improved retrieval via chunking/embedding iteration, and reduced hallucinations through citation-grounding and confidence-based abstention. Also partnered with non-technical ops staff to deliver anomaly detection/monitoring by translating operational needs into model signals, thresholds, and alerting logic.”

“ML/computer-vision practitioner who shipped a CycleGAN-based bilingual handwriting translation demo (English↔Telugu) for low-resource scripts using unpaired datasets, focusing on preserving handwriting style and real-time deployment via Gradio. Also delivered a medical imaging pipeline by fine-tuning ResNet-50 and ViT-B/16 for pneumonia detection, emphasizing reproducibility, measurable evaluation, and stakeholder-friendly iteration.”