Vetted Machine Learning Engineers

“ML engineer/data scientist who deployed a production credit risk + insurance claims triage platform at Hartford Financial, combining XGBoost default prediction with BERT-based document classification. Demonstrated strong MLOps by cutting inference latency to sub-500ms and building drift monitoring plus automated retraining/deployment pipelines (MLflow, CloudWatch, GitHub Actions, SageMaker) with human-in-the-loop review and SHAP-based explainability for underwriting adoption.”

“Production-focused applied ML/LLM engineer who has deployed an LLM-powered RAG assistant and improved reliability through rigorous retrieval evaluation (recall/MRR), reranking, and guardrails that prevent confident wrong answers. Experienced running containerized ML/LLM services on Kubernetes (including AWS-managed layers) with CI/CD and observability, and has delivered a real-time predictive maintenance system using streaming sensor data and time-series anomaly detection in close partnership with maintenance teams.”

“Built a production GPT-4/LangChain/Pinecone RAG “AI Copilot” at Northern Trust to automate financial report generation and analyst Q&A over internal structured (SQL warehouse) and unstructured policy data. Focused on real-world production challenges—grounding and latency—achieving major speed gains (seconds to milliseconds) via MiniLM embedding optimization and Redis caching, and implemented rigorous testing/evaluation with MLflow-backed metrics while aligning compliance and finance stakeholders for deployment.”

“LLM/agent engineer who built a production multi-agent research automation system using LangGraph (planner, retriever with FAISS, supervisor, evaluator) with structured outputs and citation tracking for traceable reports. Emphasizes reliability and operations—LangSmith-based observability, multi-level testing, hallucination mitigation, and latency/cost controls—plus prior experience as a Computer Vision Software Engineer at Deepsight AI Labs working directly with non-technical customers.”

“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.”

“Applied LLMs to high-stakes domains (wildfire risk for emergency teams and loan approval via a fine-tuned IBM Granite model), with a strong focus on reliability—using RAG-based cross-validation to reduce hallucinations and continuous ingestion pipelines (MODIS satellite imagery via AWS Lambda) to keep data current. Experienced in production orchestration and MLOps-style workflows using Airflow, AWS Step Functions, and SageMaker Pipelines, and collaborates closely with analysts on KPI-driven evaluation.”

“Built and deployed a production LLM/RAG system at CVS to automate clinical documents, addressing PHI compliance, retrieval accuracy, and latency; achieved a 35–40% reduction in review effort through chunking and FP16/INT8 optimization. Also has experience translating AI outputs into actionable insights for non-technical stakeholders (sports analysts).”

“Backend engineer with hands-on experience building real-time, low-latency systems: owned the Python backend for a real-time crowd-monitoring product (top 5% at HackHarvard 2025) using OpenCV, GPU YOLO inference (PyTorch), WebRTC, and OAuth. Also has production Kubernetes/GitOps experience (Helm/Kustomize, GitHub Actions, Argo CD), Kafka-based event pipelines, and executed a minimal-downtime on-prem PostgreSQL migration to AWS EC2.”

“ML/AI engineer with production experience in high-scale banking fraud detection at Truist, building an end-to-end pipeline (Airflow/AWS Glue/Snowflake, PyTorch/sklearn) with automated retraining and Kubernetes-based deployment; delivered measurable gains (22% fewer false positives, 15% higher recall) and reduced manual ops ~40%. Also partnered with clinicians at Kellton to deploy an LLM system for summarizing/classifying clinical notes, improving review time and decision speed.”

“Built a production LLM-powered workflow at Frontier to extract structured signals from messy, high-volume documents and route work to the right teams, replacing a multi-day, error-prone manual process. Emphasizes production reliability with schema/consistency validation, re-prompting and deterministic fallbacks, plus async pipeline optimizations for predictable latency. Experienced with multi-agent orchestration (LangGraph, AutoGen, CrewAI) and AWS workflow tooling (Step Functions, SQS, Lambda), and delivered ~70% safe automation via stakeholder-driven thresholds and human review.”

“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).”

“Built and deployed a production autonomous AI data analyst agent (LangChain + GPT + Streamlit on AWS) that turns natural-language questions into validated SQL, visualizations, and insights, cutting manual analysis time by ~50%. Emphasizes reliability and MLOps: schema-aware validation/guardrails to prevent hallucinations, scalable large-data processing, and Azure DevOps CI/CD + MLflow for automated deployment and experiment tracking.”

“Built production AI/RAG-style systems for message Q&A and insurance claims workflows, combining data ingestion, indexing/retrieval, and LLM integration with fallback modes. Has hands-on orchestration experience (Airflow, Prefect, LangChain) and cites large operational gains (claims processing reduced to ~45 seconds; manual review -50%; false alerts -30%) through automated, monitored pipelines and close collaboration with non-technical stakeholders.”

“AI/ML engineer with banking domain experience (M&T Bank) who built a production credit-risk prediction and reporting platform combining ML models (XGBoost/TensorFlow) with a RAG pipeline (LangChain + GPT-4) over compliance documents. Delivered measurable impact (≈20% better risk detection/precision, 50% less manual reporting) and productionized workflows on Vertex AI/Kubeflow with CI/CD and monitoring; also implemented embedding-based semantic search using FAISS/Pinecone.”

“AI/LLM engineer at Humana who built and deployed a HIPAA-aware RAG system for clinical record retrieval, cutting search time dramatically and improving retrieval efficiency by 30%. Experienced with Spark-scale data preprocessing, QLoRA fine-tuning, LangChain orchestration, and MLflow+SageMaker integration, with a strong testing/evaluation discipline (A/B tests, human eval) to hit 95%+ accuracy and production latency targets.”

“Built and deployed a production Llama 3-based RAG document Q&A system using FAISS, addressing context-window limits through chunking and keeping retrieval accurate by regularly refreshing embeddings. Has hands-on orchestration experience with LangChain and LlamaIndex for multi-step LLM workflows (including memory management) and collaborates with non-technical teams (e.g., marketing) to deliver AI solutions like recommendation systems.”

“Governance engineer intern at GSK who built policy-as-code automation using Open Policy Agent/Rego integrated into GitHub CI/CD and Terraform workflows. Also built and shipped a voice-enabled expense tracking app using speech-to-text + LLM structured extraction with strong validation, retries, and semantic guardrails, and designed the supporting PostgreSQL data model with performance-focused indexing.”

“Built and shipped a production multi-agent personal financial assistant at AlphevaAI on AWS ECS, combining FastAPI microservices, Redis/SQS orchestration, and Pinecone-based hybrid RAG (semantic + BM25) to ground financial guidance. Improved routing accuracy with an embedding-based SetFit + logistic regression intent classifier feeding an LLM router, and optimized UX with live streaming plus cost controls via model tiering and caching.”

“Built a production RAG-based healthcare chatbot to retrieve patient medical documents spread across multiple platforms, reducing manual and error-prone searching. Implemented semantic search with custom embeddings (Hugging Face) and Pinecone, deployed via FastAPI/Docker on AWS SageMaker with MLflow tracking, and optimized fine-tuning cost using LoRA while orchestrating retraining pipelines in Airflow.”

“GenAI/LLM engineer who built and deployed a production RAG system for enterprise document search and decision support, cutting manual lookup time by 40%+. Experienced with LangChain/LangGraph agent orchestration plus Airflow/Prefect for ingestion and incremental reindexing, with a strong focus on reliability (testing, observability) and stakeholder-driven metrics.”

“LLM/agent builder who shipped a live consumer AI-agent app (kalpa.chat) that visualizes complex reasoning as interactive graphs and abstracts multi-provider model usage via a unified wallet. Professionally has applied LangChain/LangGraph to IVR parsing and to scaling a football video-generation pipeline at DAZN, including shipping a VAR-specific retrieval/order fix via SQL after iterating with a non-technical PM.”

“Forward-deployed engineer who built a production AI drone-control chatbot that lets users fly a drone via natural language while viewing a real-time feed. Implemented RAG over drone SDK documentation (vector DB + top-k retrieval) and LoRA fine-tuning, with a focus on latency, token efficiency, and cost reduction, and regularly works with non-technical clients to integrate and explain AI system architecture.”

“ML/LLM engineer with Meta experience building production AI systems for near real-time user-report classification and summarization under strict latency (<250ms), safety, cost, and privacy constraints. Has hands-on MLOps/orchestration experience (Airflow, Spark, MLflow, Kubernetes, Docker, GitHub Actions) plus observability (Prometheus/Grafana) and applies rigorous evaluation, staged rollouts, and A/B testing to keep agent workflows reliable in production.”

“Built and deployed LLM-powered agentic chatbot and text-to-SQL systems using LangGraph/LangChain (and Bedrock), structuring workflows as DAGs with planning/replanning and validation to improve tool-calling reliability and reduce hallucinations. Operates production feedback loops with online/offline metrics, drift detection, and LangSmith-based evaluation pipelines, and regularly partners with business stakeholders and clinicians using slide decks and visual charts.”