Vetted OCR Professionals

“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 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.”

“ML engineer at CGI who built demand forecasting models end-to-end, from feature engineering and training through AWS deployment. Stands out for a production-first mindset and strong skepticism of AI-generated code, including catching a Copilot-generated SQL query that would have caused a costly full table scan in production.”

“Software engineer with experience at PTC (Onshape cloud CAD) and Firebolt building customer-facing features end-to-end—from user research and prototyping (tooltips, CSV imports) through deployment and usage monitoring. Also handled urgent production crashes in a Flutter mobile app across iOS/Android by diagnosing state-management conflicts and shipping a stabilizing patch; enjoys hands-on, customer-facing work and travel.”

“Built and shipped production RAG-based LLM agents automating multi-step document query workflows, emphasizing reliability via monitoring, retries, structured exception handling, and fallback retrieval (alternative embeddings/keyword search). Demonstrated measurable gains (18% latency improvement, 25% retrieval efficiency, 12% precision) and has experience integrating agents with messy tax and transaction data at RSM using validation/cleaning and idempotent design.”

Hiya Kothari

Screened

Intern Full-Stack Software Engineer specializing in AI/ML and cloud

San Francisco, CA3y exp

“Built a Python-based geospatial machine learning backend for PFAS contamination risk mapping, including reproducible feature pipelines, ensemble modeling, and a FastAPI layer for visualization/analysis. Emphasizes data integrity and robustness (CRS/coverage checks, fail-fast validation) and has led safe backend refactors using feature flags, idempotent backfills, and Postgres RLS for secure, queryable results delivery.”

Omkar Tulsidas Parab

Screened

Mid-Level Full-Stack Software Engineer specializing in web apps, data pipelines, and ML

San Francisco, CA4y exp

“Software engineer who owned an Order Management System end-to-end at Reliance Jio, improving large-table performance via UI virtualization shipped behind feature flags and refined through direct ops-user observation. Also built an OCR automation tool at Piramal Realty using Python/Tesseract with validation and manual correction fallbacks, driving adoption by operations teams. Experienced integrating with Kafka-based microservices and improving observability using structured logging and correlation IDs.”

Harshitha K

Screened

Mid-level Full-Stack .NET Developer specializing in cloud-native microservices

Greensboro, NC5y exp

“Full-stack .NET engineer with cloud and applied GenAI experience who shipped a real-time policy status tracking module at Lincoln Financial using ASP.NET Core/.NET 8, Kafka, Angular, SQL Server, Redis, and AKS autoscaling. Also delivered a production internal LLM+RAG support assistant at Honeywell with strong security/guardrails (PII masking, RBAC) and a rigorous eval/regression loop built on a 200-question gold set.”

Bala Venkateswarlu K

Screened

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

USA5y exp

“Built and deployed an LLM-powered claims-document summarization system (insurance domain) that cut agent review time from 4–5 minutes to under 2 minutes and saved 1,200+ hours per quarter. Hands-on across orchestration and production infrastructure (Airflow retraining DAGs, Kubernetes, SageMaker endpoints, FastAPI) and recent RAG workflows using n8n + Pinecone, with a strong focus on reliability, cost, and explainability for non-technical stakeholders.”

“GenAI/ML engineer with hands-on experience building production financial intelligence and document summarization systems at Citibank. Stands out for combining LLM fine-tuning, hybrid RAG, multi-agent workflows, and strong MLOps/observability practices to deliver measurable business impact, including 60% faster analyst retrieval, 31% higher precision, and 99%+ uptime.”

“Robotics/AI candidate who built an AI-driven landmark location tool during a summer internship at Mobile Drive, combining YOLOv5 object detection with OpenStreetMap-based geolocation to handle dense, cluttered urban environments. Also researched deploying LLM-based agents on constrained hardware using quantization plus LoRA/continuous learning, improving accuracy from ~80% to ~92%, with an emphasis on production logging for reliability.”

“Consulting background (Accenture) delivering technically complex solutions involving on-chain data and strict government security standards, including building isolated sandbox environments to move from PoC to production. Experienced in debugging agentic/LLM-style workflows (e.g., document scanning issues) with deterministic guardrails, preprocessing, and strong logging/monitoring. Has led large-scale crypto wallet workshops (including for the CFTC) and helped win business via clear, layered technical demos; also built internal marketing taxonomy tooling and drove adoption through cross-functional alignment.”

“At CVS Health, the candidate productionized a RAG-based LLM solution in a regulated healthcare setting, emphasizing reliable data pipelines, LoRA fine-tuning, monitoring, safety guardrails, and A/B testing. They have hands-on experience troubleshooting real-time RAG failures (e.g., chunking/embedding issues) and regularly lead developer-focused demos/workshops while translating technical architecture into business value for stakeholders.”

sarah robert

Screened

Staff RPA & Automation Engineer specializing in Financial Services

Baton Rouge, LA11y exp

“Blue Prism RPA developer in a small FinTech-aligned team who owned ~20 production bots and drove both delivery and reliability. Built a shared VDI/locking design that cut infrastructure cost ~20–30% and routinely handled ServiceNow-driven production incidents end-to-end, including hotfixes and longer-term SDLC fixes. Also acted as a player-coach, training junior hires and maintaining high bot success rates (up to 99% within SLA).”

“Software engineer who recently shipped an authentication and role-based access feature for a web app, using AI selectively for boilerplate, debugging, and test suggestions while retaining ownership of architecture, security, testing, and final review. Stands out for a disciplined, security-first approach to AI-assisted development and a pragmatic preference for lightweight API-driven solutions over unnecessary framework complexity.”

“Built and deployed a production LLM-powered RAG assistant for healthcare teams (care managers/support) to answer questions from clinical and policy documentation, emphasizing trustworthiness via improved retrieval, reranking, and strict grounding prompts to reduce hallucinations. Also has hands-on orchestration experience with Apache Airflow for end-to-end ETL/ML workflows and applies rigorous testing/metrics (hallucination rate, tool-call accuracy, latency, cost) to ensure reliable AI agent behavior.”

“LLM/ML engineer who has shipped production systems in legal/financial-risk domains at Wolters Kluwer, including a hybrid OCR+deterministic+LLM extraction pipeline that structured UCC filings at massive scale and drove $6M+ in revenue. Also built LangGraph-based multi-agent “Deep Research” workflows with model routing, tool calls (MCP), persistence, and human-in-the-loop review, and partnered closely with policy writers to deliver LLM summarization that cut writing time by ~60%.”

“Full-stack product engineer who has shipped polished customer-facing experiences across iOS (SwiftUI), web (Next.js/React/TypeScript), and Python backends. Built systems ranging from an escalating smart-reminder engine to a sub-200ms search UI over 6M+ court records, and owned AWS production operations including resolving a real DB-connection-exhaustion incident with scaling and architectural hardening.”

“Built and productionized an LLM-powered support/knowledge pipeline using embeddings and retrieval (RAG) to deliver more grounded, higher-quality responses while reducing manual effort. Focused on real-world reliability and performance—adding structured validation/guardrails, optimizing vector search and context size for latency/scale, and monitoring failure patterns in production. Experienced with orchestration via LangChain for LLM workflows and Airflow for production data/ML pipelines, and iterates closely with operations stakeholders through demos and feedback.”

“Founding/solo engineer who rebuilt an early-stage product from the ground up: Ask NETA, an AI assistant for electricians to answer complex electrical code questions. Delivered a full-stack TypeScript system (React web + React Native iOS/Android, Express API, Postgres on AWS) with CI/CD, observability, and a Vertex AI RAG pipeline, reaching 3,000 MAUs in the first month; also built a real-time distributed scoring system handling unreliable hardware data with sequencing and retries.”

“Platform/infra engineer with deep Kubernetes (EKS) and VMware vSphere experience who has led a monolith-to-microservices transition for a credit lending decision platform. Built GitOps-driven Terraform delivery with strong governance, and used LaunchDarkly-based progressive rollouts plus Datadog observability to safely ship multiple times per day (reported ~6x throughput and 1/3 the bugfix tickets vs legacy). Also operates hybrid on-prem/AWS networking (firewall + Transit Gateway, BGP) and has handled high-stakes datacenter migrations (100TB Storage vMotion) under Sev1 conditions.”

“Built and owned VividCraft end-to-end, a production AI platform spanning a TypeScript/Next.js frontend and a Python backend with FastAPI, Celery, Redis, PostgreSQL, and AWS. Stands out for reliability-focused systems thinking: designed idempotent job orchestration across 9 AI providers, shipped with extensive automated test coverage, and reports zero production regressions after launch plus zero credit loss through provider outages.”