Vetted AI Engineers in Remote

“Built a production RAG-based natural-language-to-SQL system at Global Atlantic to replace slow, expensive manual analytics ticket workflows, focusing heavily on retrieval quality and measurable evaluation (200-question ground-truth set; recall@5 improved 0.65→0.78 via semantic chunking). Also built a custom MCP-style agent orchestrator for a personal project (arxiv-ai) to improve flexibility and Langfuse-aligned observability, and has hands-on experience with LangGraph, CrewAI, and n8n.”

“AI engineer with production experience building a high-accuracy (98%) fraud detection system operating at real-time latency (1–2s) over millions of transactions, using a multi-model pipeline approach to meet performance constraints. Also implemented Airflow-orchestrated workflows (DAGs, retries, alerts) to replace brittle cron scripts and is currently pursuing a master’s project on real-time ASL-to-text conversion.”

“AI Engineer (Medtronic) who deployed a production RAG-based clinical assistant grounded in curated biomedical literature (no patient-identifiable data). Deep hands-on experience orchestrating and hardening LLM workflows with LangChain/LangGraph, including stateful agentic flows, rigorous testing, and evaluation; reports a 72% accuracy improvement through retrieval enhancements (query rewriting, multi-query expansion, MMR reranking).”

“LLM/agentic-systems engineer with PayPal experience hardening an LLM-powered fraud support assistant from prototype to production, focusing on low-latency distributed architecture, rigorous evaluation/testing, and security/compliance. Comfortable in customer-facing and GTM contexts—runs technical demos/workshops, builds tailored pilots, and aligns sales/CS with engineering to close deals and drive adoption.”

“Built and deployed a secure, production LLM-based document summarization and risk-highlighting tool for financial auditors, running inside a private Azure environment to protect confidential data. Focused on reliability (hallucination mitigation via retrieval-based prompts and source citations) and validated performance through comparisons to auditor summaries plus a user pilot, cutting review time by about half.”

“AI engineer with robotics perception experience at Forterra, building and deploying moving-object/obstacle detection models into real-time robot pipelines. Addressed training crashes/latency via sub-batch training and optimizer tuning, and improved debugging using ROS/ROS2 tooling with 3D voxel visualization and color-coded validation.”

“Built an LLM multi-agent “ingredient safety” analyzer for cosmetics that cuts consumer research time from ~20+ minutes to minutes, using LangGraph orchestration, hybrid retrieval (Qdrant + Tavily), and safety-focused critic validation (false rejections reduced ~30%→~8%). Also has research-internship experience building computer-vision pipelines to classify emerald color/clarity by translating gem-expert heuristics into quantitative model features.”

“GenAI/ML engineer in Citigroup’s finance environment who has deployed production RAG systems for investment banking under strict privacy and model-risk constraints. Built an internal-VPC Llama2 + Pinecone + LangChain solution with NER redaction and citation-based verification to prevent hallucinations, delivering major time savings, and also partnered with global finance executives to ship an AI early-warning indicator for treasury/liquidity risk.”

“Built and shipped a production Chrome extension (Promptly) that lets users select text on any webpage and transform it in place (rewrite/shorten/translate) using on-device AI plus external LLMs. Implemented a custom lightweight orchestration layer for prompt chaining, context flow, and output validation, and tackled tricky browser Selection API issues to preserve formatting while keeping the UX simple and fast.”

“LLM/agent engineer who built a production LangGraph multi-agent orchestrator connecting GitHub and APM/observability signals with a chain-of-verification loop for root-cause analysis. Emphasizes pragmatic architecture (start simple with state summaries), performance tuning (async LLM calls, Docker), and rigorous evaluation (LLM-as-judge, adversarial testing, hallucination/instruction adherence metrics, tool-call tracing) while iterating with non-technical stakeholders via A/B testing.”