Vetted Semantic Search Professionals

“Built and deployed a production RAG system for financial/compliance teams using GPT-4, Claude, and local models to retrieve and summarize thousands of internal documents with strong security controls (role-based retrieval, PII masking). Drove significant operational gains (30+ hours/week saved, ~35% productivity lift, ~45% faster responses) and orchestrated end-to-end ingestion/embedding/index refresh pipelines with Airflow, S3, and SageMaker while partnering closely with compliance stakeholders on auditability and traceability.”

“ML/LLM engineer with production experience building a RAG-based LLM support assistant (FastAPI, Redis, Kafka) with multi-layer validation and human-in-the-loop feedback loops to improve accuracy over time. Has orchestration and MLOps depth using Airflow and Kubeflow on Kubernetes (autoscaling, alerting, monitoring) and delivered measurable ops impact (40% ticket efficiency improvement) by partnering closely with customer support teams.”

“Built and shipped an AI-powered driver ranking/assignment system at AffirmoAI using LLM intent classification + RAG over pgvector/Postgres, served via FastAPI with a React UI that explains scores. Drove measurable improvements through optimization and iteration (latency down to <800ms, adoption 60%→90%+) and implemented rigorous eval loops with dispatcher ground truth plus cold-start handling for new drivers.”

Teja Babu Mandaloju

Screened

Mid-level Data Scientist/MLOps Engineer specializing in NLP, GenAI, and cloud ML platforms

Chicago, USA5y exp

“AI/ML engineer who led production deployment of a multimodal (text/video/image) RAG system on GCP using Gemini 2.5 + Vertex AI Vector Search, scaling to 10M+ documents with sub-second latency and +40% retrieval accuracy. Strong MLOps/orchestration background (Kubernetes, CI/CD, Airflow, MLflow) with proven impact on reliability (75% fewer incidents) and deployment speed (92% faster), plus experience delivering explainable ML (XGBoost + SHAP + Tableau) to non-technical retail stakeholders.”

“ML/AI engineer with hands-on ownership of fraud detection and investigator-assist systems, combining anomaly detection with RAG-based LLM summarization in production. Stands out for translating research ideas into reliable cloud-deployed workflows that improved precision to 92%, cut review time by 25-30%, and increased investigator throughput by roughly 30% while also building reusable Python infrastructure for team-wide velocity.”

“Full-stack AI engineer who has owned production deployments for both a voice journaling/emotional insights app and a RAG-based research assistant. Stands out for turning messy, failure-prone LLM and document pipelines into reliable user-facing systems through strong debugging, staged workflow design, and post-launch stabilization.”

Rohan Chodapunedi

Screened

Entry-level Data Scientist specializing in LLMs and analytics

Folsom, CA1y exp

“Built a zero-to-one AI contract/policy QA agent for compliance and data teams, with a strong emphasis on trust, traceability, and clause-level citations rather than just fluent answers. They combine full-stack product ownership with practical LLM systems design, including hybrid retrieval, structured outputs, and evaluation pipelines to improve reliability, latency, and cost.”

“Built and shipped production AI features for Aiden, including a natural-language agent and a Knowledge Hub ingestion/retrieval system. Stands out for hands-on debugging of real LLM production issues across providers like OpenAI and AWS Bedrock, improving reliability and achieving 90% response/retrieval consistency through direct LiteLLM integration, validation, monitoring, and async system design.”

“Engineer with hands-on experience embedding AI into software delivery workflows, including Claude-powered PR review, testing, debugging, and multi-agent coding pipelines. They pair AI automation with strong systems thinking around microservices, fault tolerance, multi-AZ design, caching, and security controls like WAF and rate limiting, and also experiment independently with RAG and multi-agent search projects.”

George Platon

Screened

Principal Full-Stack Engineer specializing in AI, DevOps, and cloud platforms

Romania, Romania16y exp

“Built a production end-to-end AI video-to-reels clip extraction system using a multi-agent architecture with transcription, captioning, effects generation, and centralized orchestration. Demonstrates unusually strong systems thinking around reliability, observability, evaluation, and production tradeoffs for LLM-powered workflows, including Kubernetes/Kafka-based deployment and regression-driven prompt governance.”

Kevin Delong

Screened

Senior AI/ML Engineer specializing in Generative AI, LLMs, and RAG systems

Irvine, CA12y exp

“AI/ML engineer with hands-on experience shipping production systems across fintech, travel, and legal use cases. They’ve built end-to-end chatbot, generative content, and RAG solutions on AWS with CI/CD, monitoring, and guardrails, including a loan application platform that generated $3,000 in sales in its first month.”

“Early-career engineer with undergraduate research and hospital internship experience building Python/LLM automation systems, including a Study Planner AI and internal RAG tools for messy legal and clinical data workflows. Stands out for combining web scraping, vector search, and frontend integration to replace manual CSV-heavy processes under tight timelines.”

“AI/full-stack engineer who has built zero-to-one internal products around LLMs, RAG, and NLP pipelines, including a conversational data interface and a production AI agent system. Stands out for combining frontend UX for non-technical users with backend/cloud architecture and measurable impact, including a reported 60% reduction in data retrieval time.”

“Director-level product leader with experience spanning SaaS platform rebuilds, pricing strategy, and AI-native workflow design. At Skykit, they led a major self-serve/PLG account management transformation across multiple teams, and they also built an AI sales quoting tool using a multi-stage RAG pipeline that reached 100% quote accuracy in user testing.”

Godwin Idowu

Screened

Intern Software Engineer specializing in AI/ML and full-stack systems

Gambier, OH4y exp

“Full-stack engineer with hands-on ownership of both real-time marketplace features and production AI systems. Built AI-powered matching at an early-stage startup and shipped LLM-driven CRM and competitive intelligence workflows using OpenAI, LangChain, and RAG, with measurable gains in engagement, workflow reduction, and decision speed.”

“Backend-focused software engineer building distributed, event-driven Java/Spring Boot microservices with Kafka for low-latency, high-frequency processing. Has hands-on experience modernizing a legacy Java system into containerized microservices deployed on Kubernetes with GitHub Actions CI/CD, and has integrated retrieval-based AI components into production workflows; no ROS/robot hardware experience yet.”

“Built and deployed a production RAG-based enterprise document intelligence platform for financial/compliance/operational documents on AWS (Spark/Glue ingestion, embeddings + vector DB, LangChain orchestration, REST APIs on Docker/Kubernetes). Deep hands-on experience orchestrating multi-step and multi-agent LLM workflows (LangChain, LangGraph, CrewAI) with strong focus on grounding, evaluation, observability, and cost/latency optimization, and has partnered closely with non-technical finance/compliance teams to drive adoption.”

“At onedata, built and deployed an LLM-powered, multi-agent analytics platform on AWS Bedrock that lets users create Amazon QuickSight dashboards through natural-language conversation, cutting dashboard build time from ~30 minutes to ~5 minutes. Strong in production concerns (observability, token/cost tracking, model tradeoffs) and in bridging business + technical work, owning pre-sales pitching through delivery with an engineering management background focused on AI product management.”

“ML/NLP engineer with hands-on experience building production systems for unstructured insurance claims and customer data linking. Delivered measurable impact at scale (millions of documents), combining transformer-based NLP, vector search (FAISS/Pinecone), and human-in-the-loop validation, and has strong production workflow/observability practices (Airflow, AWS Batch, Grafana/Prometheus).”

“ML/NLP engineer (Beyond Identity) who built production semantic search and entity-resolution systems over internal security documentation, using LDA + BERT embeddings with FAISS/Pinecone to cut search time by 30%. Also scaled a real-time anomaly detection pipeline to millions of events/day with Spark and AWS Lambda, with strong emphasis on measurable validation (Precision@k, MRR, F1, ARI).”

“Infrastructure/DevOps engineer (Geico) focused on AWS and Kubernetes at production scale. Has hands-on experience building secure GitHub Actions CI/CD for EKS, provisioning core AWS infrastructure with Terraform/CDK, and leading end-to-end incident response with post-incident automation to prevent recurrence; no direct IBM Power/AIX/PowerHA experience.”

“Built and operated a real-time student event/party discovery platform with map-based search, RSVP, and authentication using React/TypeScript, Node.js, and Firebase Firestore. Demonstrates strong backend correctness under concurrency (transactions, idempotency, retries/backoff) and solid API product thinking (versioning, Swagger docs, structured errors, cursor pagination), including custom geospatial querying via Haversine filtering.”

“Consulting-style LLM practitioner who builds enterprise knowledge assistants using RAG and takes them from prototype to production with guardrails, evaluation, and full-stack observability. Experienced partnering with IT and customer-facing teams to demo solutions, build tailored prototypes, and drive adoption through API-based integration.”

“Built a production AI legal search platform that uses a retrieval-first, source-grounded LLM pipeline with confidence-based fallbacks and structured, traceable outputs to reduce hallucinations and improve trust. Also has experience at Discover Excellence building real-time analytics and identity stitching systems, emphasizing conservative data validation, idempotent processing, and fault-tolerant queue-based workflows.”