Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm a Senior AI/ML Engineer with over 10 years of experience, specializing in architecting and deploying large-scale AI systems across LLMs, multi-agent AI, computer vision, and cloud-native MLOps. I design production-grade pipelines with RAG, distributed fine-tuning, vector databases, and automated CI/CD across Azure, AWS, and GCP to accelerate deployment and improve accuracy. I excel at turning complex research into scalable enterprise solutions, mentoring cross-functional teams, and driving measurable technical impact. My work spans geospatial analytics, model optimization, HITL safety loops, and robust observability, all aimed at delivering reliable, compliant AI in production.…I'm a Senior AI/ML Engineer with over 10 years of experience, specializing in architecting and deploying large-scale AI systems across LLMs, multi-agent AI, computer vision, and cloud-native MLOps. I design production-grade pipelines with RAG, distributed fine-tuning, vector databases, and automated CI/CD across Azure, AWS, and GCP to accelerate deployment and improve accuracy. I excel at turning complex research into scalable enterprise solutions, mentoring cross-functional teams, and driving measurable technical impact. My work spans geospatial analytics, model optimization, HITL safety loops, and robust observability, all aimed at delivering reliable, compliant AI in production.

Jeremiah Medina

Full Stack Developer, Developer, AI Engineer, +7





I'm a Senior AI/ML Engineer with over 10 years of experience, specializing in architecting and deploying large-scale AI systems across LLMs, multi-agent AI, computer vision, and cloud-native MLOps. I design production-grade pipelines with RAG, distributed fine-tuning, vector databases, and automated CI/CD across Azure, AWS, and GCP to accelerate deployment and improve accuracy. I excel at turning complex research into scalable enterprise solutions, mentoring cross-functional teams, and driving measurable technical impact. My work spans geospatial analytics, model optimization, HITL safety loops, and robust observability, all aimed at delivering reliable, compliant AI in production.…I'm a Senior AI/ML Engineer with over 10 years of experience, specializing in architecting and deploying large-scale AI systems across LLMs, multi-agent AI, computer vision, and cloud-native MLOps. I design production-grade pipelines with RAG, distributed fine-tuning, vector databases, and automated CI/CD across Azure, AWS, and GCP to accelerate deployment and improve accuracy. I excel at turning complex research into scalable enterprise solutions, mentoring cross-functional teams, and driving measurable technical impact. My work spans geospatial analytics, model optimization, HITL safety loops, and robust observability, all aimed at delivering reliable, compliant AI in production.

Available to hire

I’m a Senior AI/ML Engineer with over 10 years of experience, specializing in architecting and deploying large-scale AI systems across LLMs, multi-agent AI, computer vision, and cloud-native MLOps. I design production-grade pipelines with RAG, distributed fine-tuning, vector databases, and automated CI/CD across Azure, AWS, and GCP to accelerate deployment and improve accuracy.

I excel at turning complex research into scalable enterprise solutions, mentoring cross-functional teams, and driving measurable technical impact. My work spans geospatial analytics, model optimization, HITL safety loops, and robust observability, all aimed at delivering reliable, compliant AI in production.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Work Experience

Senior Software Engineer at Aspect Software

June 30, 2025 - July 30, 2025

Streamlined integration of external data sources using APIs like Shopify, reducing data setup time by 50%. Developed AI-powered data mapping tools that increased data import accuracy by 35%, improving the WorkforceOS™ platform usability. Architected a dynamic forecasting and what-if analysis engine enhancing forecast reliability by 45%, supporting strategic decision-making. Enhanced real-time analytics dashboard boosting agent productivity by 30% through improved visualizations and interactions. Implemented gamification features raising user engagement and satisfaction by 40% in contact center environments. Improved collaborative tools via in-app messaging and tagging, reducing communication lag by 25%. Led API integrations with leading CRM systems, expanding platform capabilities by 20%.

Full Stack Engineer at Innoxstax Tech LLC

July 31, 2022 - July 30, 2025

Led development of custom B2B software, improving project delivery timelines by 40%. Engineered agile data processing workflows that enhanced data throughput and reliability by 60%. Pioneered mobile and web app projects, boosting user adoption by 35%. Revamped data ingestion pipelines, increasing efficiency by 50% and reducing downtimes. Integrated AI tools into digital transformation services, increasing innovation and client value by 25%.

Software Engineer at Oracle

February 29, 2020 - July 30, 2025

Optimized backend services for Oracle Database analytics, enhancing data retrieval speeds by 25%. Contributed AI feature deployments in Oracle SaaS ecosystem, increasing responsiveness by 20%. Implemented cost-effective hosting strategies on Oracle Cloud, reducing deployment expenses by 30%. Enhanced platform stability for Oracle Fusion Cloud ERP, improving uptime reliability and customer satisfaction by 15%.

Junior Web Developer at OVP Health

June 30, 2018 - July 30, 2025

Developed responsive web applications for healthcare services, improving patient satisfaction by 30%. Enhanced telemedicine platforms, increasing patient accessibility by 20%. Engineered robust data validation ensuring CARF compliance and reducing errors by 15%. Automated medical data ingestion workflows, accelerating data availability by 40%. Designed user-friendly admin tools to streamline patient record management and cut processing time by 25%.

Senior AI/ML Engineer at T-Mobile

November 1, 2025 - November 1, 2025

Engineered and deployed a multi-agent AI system integrating LLMs (GPT5) with Object Detection, Computer Vision, and Depth Estimation to detect anomalies between construction drawings and drone images, improving inspection accuracy by 35%. Built MCP tools on Azure Cloud (Azure Functions, Cosmos DB, PostgreSQL, PostGIS) for scalable data storage and real-time geospatial analytics. Designed ETL pipelines to validate, sort, and categorize over 10M+ construction documents stored in AWS S3, integrated with Databricks for indexing and analytics; enhanced content extraction via Azure Document Intelligence and Azure Content Understanding. Implemented distributed fine-tuning pipelines for open-source LLMs (Llama, Gemma) on GCP Vertex AI using QLoRA and Instruction Tuning, accelerating convergence by 45% and reducing domain hallucinations by 40%. Applied Retrieval-Augmented Generation (RAG) and FAISS indexing to optimize document-based anomaly detection, reducing false positives by 25%. Collabora

Senior AI Engineer at Function Health

September 1, 2025 - September 1, 2025

Led the design and deployment of a HIPAA-compliant, multi-agent Voice AI assistant for clinical applications using LangChain and LangGraph to orchestrate complex reasoning and flows over LiveKit. Architected a Hybrid Retrieval-Augmented Generation (RAG) system using PgVector (PostgreSQL) and HNSW-based indexing, integrating metadata filtering and a TinyBERT reranker to reduce non-grounded (hallucinated) responses by 35% and boost retrieval precision by 40%. Pioneered Generative AI Guardrails and custom safety checker models into production, ensuring regulatory compliance and preventing toxic outputs. Implemented a continuous RLHF pipeline (PPO) to fine-tune the LLM’s multi-step reasoning, improving diagnostic accuracy by 25%. Managed the MCP server layer with LiveKit and Tavily Search Tool integration for real-time, grounded voice interactions. Mentored junior ML Engineers and Data Engineers on advanced Generative AI concepts and scalable production practices.

AI Engineer at Infor

June 1, 2022 - June 1, 2022

Applied transformer-based architectures (BERT, DistilBERT, GPT, T5) with domain-specific fine-tuning (legal contracts, support tickets, semantic search); built evaluation pipelines with metrics like ROUGE and BERTScore. Created an LLM-powered summarization tool for financial news, reducing analysts’ research time from 3 hours to 45 minutes; developed a containerized BERT-based NER model (TensorFlow/spaCy) for automated extraction from financial documents, lowering manual error rates from 11% to 2%. Built end-to-end MLOps pipelines on AWS (SageMaker, Lambda, ECR, S3, API Gateway) with GitLab CI/CD, reducing model release cycles from 1 week to under 4 days. Developed an AI-driven workforce scheduling platform using RL and time-series forecasting (Prophet, PyTorch), improving labor utilization by 25% and reducing overtime by 18%. Established evaluation and monitoring (Weights & Biases on AWS EKS) to track drift and performance for critical NLP systems.

AI Engineer Intern at Microsoft

December 1, 2017 - December 1, 2017

Implemented core tokenization and POS-tagging modules to preprocess large-scale corpora; built Named Entity Recognition (NER) pipelines. Trained and evaluated a Word2Vec embedding model on Microsoft data, improving entity classification F1 by ~8%. Designed a Seq2Seq model with attention for paraphrase generation and basic text summarization, validating on held-out data. Built an end-to-end ETL pipeline to ingest raw text logs into a Data Lake for downstream NLP modeling.

Data Engineer at Amazon

July 1, 2015 - July 1, 2015

Built and maintained ETL pipelines in Python to process terabytes of raw customer interaction and e-commerce logs into structured data stores for analytics and ML modeling. Orchestrated workflows with failure-recovery logic for reliability. Designed feature engineering pipelines for unstructured text (TF-IDF) enabling sentiment analysis and product recommendations; prototyped and deployed recommender systems including matrix factorization and basic autoencoders. Implemented K-means clustering for user segmentation and decision-tree/XGBoost models for ranking, contributing to measurable CTR improvements. Created dashboards in Tableau to monitor KPIs such as pipeline latency and model performance.

I Engineer at Infor

June 1, 2022 - June 1, 2022

Applied transformer-based architectures (BERT, DistilBERT, GPT, T5) with domain-focused fine-tuning; built an LLM-powered summarization tool and a BERT-based NER model; developed end-to-end MLOps pipelines on AWS and implemented an AI-driven workforce optimization platform.

I Engineer Intern at Microsoft

December 1, 2017 - December 1, 2017

Implemented core Tokenization and POS-tagging modules; trained Word2Vec embeddings; designed a Seq2Seq model with Attention for paraphrase generation and built an ETL pipeline to support NLP modelling.

Senior AI /ML Engineer | Technical Lead at Andor Health

June 1, 2023 - November 1, 2025

Owned the end-to-end Agentic AI product lifecycle from architecture and roadmap to production deployment and post-launch optimization. Led cross-functional teams of ML engineers, data engineers, and backend engineers; mentored junior staff; designed the Digital Front Door system, a multi-agent voice AI assistant for patients, using the Microsoft Agent Framework to orchestrate complex reasoning and conversational flows over LiveKit. Implemented a hybrid Retrieval-Augmented Generation system with PgVector and HNSW indexing to handle health queries, reducing hallucinations and improving response relevance. Built and deployed Model Context Protocol tools to retrieve real-time, up-to-date healthcare data, integrated HIPAA-compliant guardrails, and introduced a HITL feedback loop with MLflow for continuous improvement.

Senior AI Engineer at Amdocs

March 1, 2020 - May 1, 2023

Developed and deployed an AI-powered customer service system, leveraging fine-tuned GPT models with LoRA on HuggingFace to improve engagement. Optimized model performance via distillation, quantization, and pruning; built end-to-end MLOps pipelines for real-time data ingestion and auto-scaling inference on AWS SageMaker with MLflow; supported cross-functional projects including conversational AI and automation.

AI Engineer at Qualcomm

September 1, 2018 - February 1, 2020

Led development of AI-powered camera features for mobile devices, including real-time object recognition, enhanced low-light photography, and AI-driven image stabilization. Implemented CNNs and other ML models, optimized for edge deployment via TensorFlow Lite and ONNX; accelerated performance using Adreno GPU and Hexagon DSP.

Data Engineer at Amazon

May 1, 2013 - July 1, 2016

Built scalable ETL pipelines using Python, Airflow, and Pandas; developed predictive analytics models with scikit-learn and XGBoost to forecast customer churn and product usage. Integrated Python-based ML extensions (TabPy) into Tableau dashboards; automated anomaly detection using Random Forest and Autoencoders, reducing manual investigation time and enabling data-driven decisions.

Senior AI/ML Engineer | Technical Lead at Andor Health

June 1, 2023 - November 1, 2025

Led the end-to-end lifecycle of the Agentic AI product, architecting scalable systems and delivering production-grade multi-agent AI pipelines. Directed a cross-functional team of ML Engineers, Data Engineers, and Backend Engineers, conducting design reviews and ensuring high delivery quality across parallel streams. Spearheaded the Digital Front Door, a multi-agent voice AI assistant for patients built on Microsoft Agent Framework orchestrating reasoning and conversational flows over LiveKit. Implemented a hybrid Retrieval-Augmented Generation system using PgVector and HNSW indexing to improve health-domain query relevance and reduce hallucinations by ~20%. Built MCP tools (Tavily Search and EHRs tool) to retrieve real-time clinical data via Azure Functions integrated into workflows. Integrated HIPAA-compliant guardrails with a TinyBERT-based safety checker. Developed an evaluation pipeline with LLM-as-a-Judge and traditional metrics (ROUGE, BLEU, BERTScore) using Azure Evaluators; es

Senior AI/ML Engineer at Andor Health

February 1, 2024 - Present

Architected and delivered a real-time multi-agent voice GenAI assistant using LangChain and LiveKit; fine-tuned LLMs on distributed multi-GPU Azure ML with NVIDIA H100s and DeepSpeed; designed hybrid retrieval RAG pipeline with Qdrant and HNSW indexing; developed Model Context Protocol (MCP) tools for real-time EHR ingestion and structured data retrieval; built repeatable evaluation pipelines with LLM-as-a-Judge and traditional metrics; established LLMOps and observability with Prometheus and Grafana; HITL feedback loops; optimized inference with TensorRT-LLM; mentored cross-functional teams.

AI Engineer at Databricks

September 1, 2018 - December 1, 2019

Contributed to MLflow core components, improving experiment tracking reliability; optimized Databricks Runtime for ML for distributed workloads; developed scalable ML pipelines with TensorFlow and PyTorch; containerized ML workloads with Docker; implemented Kubernetes-based orchestration for experimentation workflows; engineered data preprocessing/feature engineering to boost model accuracy; automated monitoring/logging of ML experiments and deployments.

Education

Bachelor’s Degree at Marshall University

September 1, 2016 - May 31, 2020

Master of Science (MSc) in Computer Science at Marshall University

September 1, 2015 - August 1, 2017

Bachelor of Science (BS) in Computer Science at University of California, Berkeley