Vetted Embeddings Professionals

“New grad who shipped an LLM-powered writing app (“Write-it”) to production on Azure with CI/CD (GitHub Actions + JFrog) and implemented an unconventional RAG pipeline to prevent repetitive prompts using embeddings and cosine similarity. Also participated in a Luma AI image/video generation hackathon, iterating with artist feedback and improving usability by rewriting non-technical prompts via an LLM.”

“Full-stack engineer who shipped and owned a production Document Chat feature built with Next.js App Router/TypeScript and a Node/Express RAG backend, including JWT-secured route handlers and streaming responses. Demonstrated strong post-launch ownership by improving latency (~30%) via MongoDB indexing/query optimization and reducing AI costs through caching, backed by profiling with React Profiler and Chrome DevTools.”

“Software engineer (internship experience) who built and owned an AWS serverless multi-user “challenge” feature end-to-end (UI + REST APIs + DynamoDB + deployment), delivering measurable gains in latency (-30%), debugging time (-50%), and join drop-offs (~-30%). Also productionized a multilingual RAG-based QA system with vector retrieval and guardrails, improving accuracy to ~85% and driving ~20% DAU growth.”

“Built and owned a production RAG-based internal knowledge assistant end-to-end, from experimentation through cloud deployment and monitoring. Demonstrated strong practical GenAI judgment by choosing prompt optimization and retrieval tuning over fine-tuning for dynamic data, driving a 40% to 50% reduction in time to answer while improving relevance, lowering hallucinations, and increasing productivity.”

“Built an end-to-end agentic population health strategy copilot for healthcare leadership, turning broad chronic disease questions into structured, evidence-backed strategy briefs. Stands out for combining healthcare domain knowledge with production-grade GenAI implementation, including LangGraph orchestration, Databricks/MLflow deployment, human review, and quality gates focused on citations, metrics, risks, and safety.”

SIVA RAMAKRISHNA PALADI

Screened

Mid-level AI/Full-Stack Engineer specializing in agentic AI and RAG systems

Santa Clara, CA5y exp

“Solo builder who shipped two ambitious AI products from scratch: Zoly, a healthcare/pharmacy automation platform with voice agents, RAG, clinician dashboard, and patient app live in 4 months, and Breeth, a contextual memory system for AI agents deployed on AWS. Particularly compelling for teams needing a hands-on full-stack/AI engineer who can operate in ambiguity, design for safety and compliance, and turn complex agent workflows into production products.”

“New grad software engineer who has already built both a full-stack location-based social app and an internal AI on-call copilot using OpenAI and LangChain. Stands out for combining end-to-end product execution with practical LLM engineering, including RAG, fallback design, citations, and production evals, plus shipping a hackathon-winning MVP in 24 hours.”

“Student technologist building production-oriented AI products, including a college guidance chatbot for Track2College and a voice-based travel assistant. Strong hands-on experience with RAG systems, FastAPI backends, TypeScript frontends, retrieval evaluation, and tool-using LLM workflows, with a clear focus on grounded, reliable user experiences.”

“Built a production multi-agent RAG assistant using LangChain/LangGraph with OpenAI embeddings and FAISS, focusing on retrieval quality and latency (Redis caching, parallel retrieval, precomputed embeddings). Experienced orchestrating ETL/ML pipelines with Airflow and Databricks Workflows, and has delivered an AI assistant for business ops to extract insights from policy/compliance documents through close non-technical stakeholder collaboration.”

“Product-minded full-stack engineer with hospitality tech experience who owned and scaled a multi-region guest verification/check-in workflow (ID/passport scanning, OCR, and government submissions) and built internal tools that cut manual entry up to 80%. Also built a React/TypeScript + FastAPI RAG “second brain” with async ingestion workers and an event-driven e-folio email microservice hardened with idempotency and retries.”

“Built and deployed a production AI-powered personalized learning platform (Django + FastAPI) featuring an LLM+RAG tutoring assistant and automated grading. Demonstrates strong applied LLM reliability engineering (structured JSON outputs with Pydantic validation, hallucination control via FAISS-based RAG thresholds and refusals) plus scalable async microservice design and Airflow-orchestrated ETL across AWS/GCP.”

Rizwana Shaik

Screened

Mid-level Full-Stack Software Engineer specializing in cloud-native apps and AI copilots

Dallas, TX4y exp

“Internship project building and deploying a LLaMA-based, RAG-enabled copilot inside a Professional Services Automation platform, enabling natural-language navigation, text-to-SQL reporting, and project/resource/budget insights across multiple modules. Addressed real production issues like context drift and vague queries with hybrid search, metadata enrichment, and an intent classification/rewriting layer, orchestrated via Apache Airflow—ultimately cutting PMO reporting time by 40%.”

Tharun Chowdary Malepati

Screened

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

5y exp

“AI/LLM engineer who built and deployed a production healthcare RAG chatbot ("DoctorBot") with strict medical safety guardrails, an 85% confidence-gated verification layer, and latency optimizations that cut responses from ~8s to ~2–3s. Also worked on finflow.ai to generate finance/banking test cases from BRDs, collaborating closely with non-technical domain stakeholders, and has hands-on orchestration experience with LangChain/LangGraph and agentic evaluation/monitoring practices.”

“Gameplay/network engineer based in Argentina who has shipped across Unity and UE5, with standout work in deterministic simulation, authoritative multiplayer, and fully local AI-driven NPC systems. Particularly compelling for teams building systemic gameplay or real-time interactive experiences: they replaced Unity physics with a custom deterministic race pipeline, improved WebGL load performance, and later built an engine-agnostic local LLM/TTS/lip-sync stack for conversational NPCs.”

“AI/ML engineer with hands-on experience owning production deployments from discovery through post-launch stabilization, including real-time computer vision/OCR systems and LLM-powered RAG workflows. Stands out for translating messy customer workflows into reliable backend services, debugging non-deterministic retrieval issues, and hardening AI systems with validation, monitoring, and human-review fallbacks.”

“Full-stack JavaScript engineer with hands-on ownership of a retail loyalty platform spanning Next.js on Vercel and NestJS microservices on Azure. Stands out for designing complex real-time and event-driven flows, including Bluetooth-connected React Native work, shared TypeScript contracts across frontend/backend, and production reliability patterns like webhooks, revalidation, logging, and retry Cron jobs.”

Xuebin Dong

Screened

Mid-level Software Engineer specializing in distributed systems and healthcare data platforms

San Diego, CA4y exp

“Full-stack and AI engineer who built both a large-scale clinical imaging dataset exploration engine and DMP Chef, an open-source LLM product for generating funder-compliant Data Management Plans. Stands out for combining strong product ownership, data-intensive backend architecture, and practical LLM systems work with retrieval, structured outputs, evals, and human-in-the-loop compliance safeguards.”

“Built a production-grade clinical and insurance document AI system in a HIPAA/PHI-regulated environment, taking it from experimentation through Azure deployment, monitoring, and iterative improvement. Stands out for translating RAG/LLM research into reliable microservices with strong safety controls, drift monitoring, and human-in-the-loop workflows that cut manual review time by 60-70%.”

“ML/AI engineer with hands-on experience building healthcare and fraud-detection systems from experimentation through deployment, monitoring, and retraining. Stands out for combining real-time IoT pipelines, cloud-native MLOps, and GenAI/RAG in regulated healthcare settings, with reported impact including reduced emergency response times and a 25% reduction in manual diagnosis time.”