Vetted Natural Language Processing Professionals

“Built a production multimodal LLM system (Gemini on GCP) to automate behavioral coding of family-involved science experiment videos, including preprocessing for inconsistent lighting/audio and LangGraph-orchestrated parallel workflows. Also developed rubric-based AI grading workflows and partnered closely with non-technical education stakeholders through explainability-focused walkthroughs and manual-vs-AI evaluation alignment.”

“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.”

“Built and deployed a production LLM-powered calorie-counting chatbot that turns plain-English meal descriptions into normalized food entities, quantities, and calorie estimates using a hybrid transformer + rule-engine pipeline. Emphasizes reliability with schema/constraint guardrails, confidence-based routing (including embedding similarity search fallbacks), and strong observability/metrics (hallucination rate, calibration, latency, cost). Partnered closely with nutritionists to encode domain standards into mappings and validation logic.”

“Built and owned a production-scale AI-driven software release/version intelligence platform orchestrated via GitHub Actions that tracks 1000+ upstream repositories and automatically generates SLA-bound JIRA upgrade tickets for hardened container images. Replaced brittle regex/PEP440 parsing with an LLM-based semantic filtering layer plus deterministic validation to handle noisy/inconsistent GitHub tags at scale, with monitoring for coverage, latency, and correctness validated against upstream ground truth.”

“AI engineer who has shipped production LLM systems across customer service and marketing use cases—building a RAG app on Azure OpenAI and speeding retrieval with Redis caching tied to Okta sessions. Also implemented a LangGraph multi-agent workflow that pulls image context from Figma to generate structured HTML marketing emails, adding a verification agent to improve image-selection accuracy while optimizing solution cost for business stakeholders.”

“LLM/agent engineer who has deployed a production internal assistant to reduce employee inquiry resolution time while maintaining regulatory compliance. Experienced with RAG, hallucination risk triage, and graph-based orchestration (LangGraph) for enterprise/banking-style workflows, emphasizing schema-validated, citation-backed, tool-constrained agent designs and tight collaboration with non-technical business/compliance stakeholders.”

“Built and deployed a production-style vision-language pipeline that generates structured medical reports from chest X-rays using BioViLT embeddings, an image-text alignment module, and BiGPT fine-tuned with LoRA, delivered via Streamlit and hosted on AWS EC2. Also collaborating experience presenting EDA findings, feature importance, and model performance to Ford managers while working with vehicle parts data at Bimcon.”

“Built a web-based online Sudoku game in JavaScript (multiplayer format supporting up to 6 teams with up to 5 players each) and demonstrates strong product/analytics orientation. Uses a KPI-driven approach (DAU/WAU, ARPU, session duration, LTV) and structured prioritization methods (MoSCoW, story mapping, cost of delay, DFV) to iterate toward targets; seeking a remote role around $70k/year.”

“Master’s-in-Data-Science candidate (UHV) with 4+ years in AI engineering building production LLM and multimodal systems. Designed an LLM-powered workflow automation platform using RAG over vector stores with guardrails (schema/output validation, fallbacks) and a rigorous evaluation/monitoring framework including drift tracking and shadow deployments. Experienced orchestrating large-scale vision-language pipelines with Airflow and Kubernetes (OCR, distributed training) and partnering with non-technical ops stakeholders to cut cycle time and reduce errors.”

“Backend/platform engineer who owned a real-time customer analytics microservice stack in Python/FastAPI with Kafka streaming into PostgreSQL, including schema enforcement (Avro) and high-throughput optimizations. Strong Kubernetes + GitOps practitioner (EKS/GKE, Helm, Argo CD) who has handled CI/CD reliability issues with automated pre-deploy checks and rollbacks, and supported major migrations (on-prem to AWS; VM to EKS) with blue-green cutover planning.”

“Built a production, agentic multi-agent pharmaceutical intelligence system for US oncology (breast cancer) conference/news intelligence, automating MSL-style information gathering and summarization for pharma and healthcare stakeholders. Uses CrewAI + LangChain orchestration, custom scraping across ~15 pharma newsrooms, and a grounding-score evaluation approach (sentence transformers/cosine similarity) to mitigate hallucinations.”

“Backend engineer with Citi Bank experience building and operating a Python/Flask Personal Finance Manager platform at 1M+ transactions/month. Strong in secure API design, database performance tuning (PostgreSQL/Azure SQL), and production reliability (92%+ test coverage, load testing, monitoring). Also integrated an NLP expense-tagging microservice with caching, background workers, autoscaling, and multi-tenant isolation via RLS and tenant-aware JWT.”

“Designed and deployed an enterprise LLM-powered clinical/pharmacy policy knowledge assistant at CVS Health, replacing manual searches across PDFs/Word/SharePoint with a HIPAA-compliant RAG system. Built end-to-end ingestion and orchestration (Airflow + Azure ML/Data Lake + vector index) with PHI masking, versioned re-embedding, and production monitoring (Prometheus/Grafana), and partnered closely with clinicians/compliance to ensure policy-grounded, auditable answers.”

“Built and deployed a production LLM-powered clinical note summarization system used by care managers to speed review of 5–20 page unstructured medical records. Implemented safety-focused validation (prompt constraints, rule-based and section-level checks, human-in-the-loop) to reduce hallucinations while maintaining low latency and meeting privacy/regulatory constraints, integrating via APIs into existing clinical tools.”

“Space/heliophysics ML engineer who built a PyTorch GRU model to propagate solar wind from L1 to the magnetopause with probabilistic outputs for uncertainty quantification, achieving ~25% better CRPS than standard approaches. Also developed production-grade Python ETL and an open-source telemetry processing package for a mission (LEXI), using Docker and GitHub Actions CI/CD and iterating with scientist/engineer stakeholders.”

“ML practitioner with hands-on experience in healthcare time-series modeling (CGM-based blood glucose prediction) including a novel ICA-based blind source separation approach and robust data-cleaning for noisy, missing sensor data. Also built an embeddings + LLM-powered podcast recommendation workflow using YouTube transcript scraping and Vellum AI document indexing, with a strong emphasis on production-grade engineering practices (TDD, monitoring) and realistic rolling validation for forecasting.”

“AI/ML engineer with production experience building a RAG-based internal analytics assistant (Databricks + ADF ingestion, Pinecone vector store, LangChain orchestration) deployed via Docker on AWS SageMaker with CI/CD and MLflow. Strong focus on real-world constraints—latency/cost optimization (LoRA ~60% compute reduction), hallucination control with citation grounding, and enterprise security/governance. Previously at Intuit, delivered an interpretable churn prediction system (PySpark/Databricks, Airflow/Azure ML) that improved retention targeting ~12%.”

“Backend/Python engineer who owned an end-to-end FastAPI + AWS internal natural-language document Q&A system (Textract extraction, embeddings/vector DB, LLM integration) with strong focus on reliability and latency. Hands-on with Kubernetes + GitOps (Argo CD, Helm, rolling updates/auto-rollback) and built/optimized Kafka streaming pipelines using Prometheus/Grafana. Also supported a zero-downtime on-prem to cloud migration with parallel run and gradual traffic cutover.”

“Operations/product-and-engineering leader who has repeatedly retooled early-stage/growing orgs (Open English, Metrc) to scale by implementing Scrum/Kanban, building metrics-driven decision systems, and upgrading teams with experienced product/engineering leadership. At Metrc, used data to drive executive alignment, established scrum teams and a 2-week cadence within 30 days, and helped burn down years of backlog/bugs while improving customer survey feedback within 3 months.”

“ML/LLM engineer at Charles Schwab who built a production loan-advisor chatbot integrated with internal knowledge and loan-calculator APIs, adding strict numeric validation to prevent rate hallucinations and optimizing context to control costs. Also runs ~40 Airflow DAGs orchestrating retraining/ETL/drift monitoring with an automated Snowflake→SageMaker→auto-deploy pipeline, and uses rigorous testing plus canary rollouts tied to business metrics and compliance constraints.”

“ML/NLP practitioner focused on insurance/claims analytics for a large financial firm, working with millions of fragmented structured and unstructured records. Built production-grade pipelines for entity extraction, entity resolution, and semantic search using Sentence-BERT + vector DB, including fine-tuning with contrastive learning (reported ~15% recall lift) and scalable ETL/containerized deployment on Kubernetes.”

“ML/NLP practitioner who built customer-feedback topic modeling (NMF + TF-IDF) to diagnose chatbot-to-agent handovers and drove product/ops changes that reduced operational costs by 20%. Also developed LSTM-based intent recognition using Word2Vec/GloVe embeddings for semantic linking, and deployed an LSTM autoencoder for fraud anomaly detection that cut false positives by 25% while capturing 15% more fraud in A/B testing.”

“Built an AI-driven insurance policy summarization platform at Marsh, taking it end-to-end from messy PDF ingestion/OCR and custom extraction through LLM fine-tuning and AWS SageMaker deployment. Delivered measurable impact (25% reduction in manual review time, 99% uptime) and demonstrated strong production MLOps/LLMOps practices with Airflow/Step Functions orchestration, rigorous evaluation (ROUGE + human review), and continuous monitoring for drift, latency, and hallucinations.”

“AI/ML engineer who built a production RAG-based internal document intelligence assistant (LangChain + Pinecone) to let employees query enterprise reports in natural language. Demonstrated hands-on pipeline orchestration with Apache Airflow and tackled real production issues like retrieval grounding and latency using tuning, caching, and token optimization, while partnering closely with non-technical business stakeholders through iterative demos.”