Vetted Research Assistants in the Chicago Metro

“Amazon internship experience building production GenAI analytics for the returns organization: a multi-agent LLM+RAG system that let analysts query multiple heterogeneous data sources in natural language without hand-written SQL. Also built and operationalized four Apache Airflow DAGs for large-scale ETL, emphasizing observability and freshness-aware metadata to keep outputs accurate and up to date.”

“Applied Scientist with legal-tech experience who builds production LLM systems. Created and deployed Quibo AI, a LangGraph-based multi-agent pipeline that turns large markdown/Jupyter inputs into polished blogs and social posts, overcoming context limits via ChromaDB + HyDE RAG. Also built a large-scale iterative code-evolution workflow using multi-model orchestration (GPT/Claude/Gemini) with testing, debugging loops, and evaluation/observability practices.”

“Robotics software engineer who built an open-source, real-time Cartesian controller for Universal Robots UR5/UR5e, targeting sub-mm accuracy at 500 Hz within ROS2/ros2_control. Demonstrates strong real-time debugging skills (timing profiling, singularity handling with Tikhonov regularization) and sim-to-real iteration using Gazebo/Isaac Sim plus physical hardware tuning; also has ROS1 experience building URDF/xacro and EKF configs for an underwater vehicle and has developed drone/robot packages.”

“AI/ML practitioner with experience spanning audio/LLM applications (built "Iota" using Whisper, tiktoken, and a local Ollama-served LLM) and healthcare ML (Facemed.ai; UChicago Radiology). Demonstrates a production-oriented mindset—focus on data/model fit, deterministic field testing, and operational safeguards—and has improved research evaluation workflows via a hash-table-based concurrent model tracking approach.”

“PhD-trained engineer with ~3.5 years of consulting experience building simulation/ML-driven manufacturing software. Deployed an ML surrogate model as a .NET C# DLL integrated with MES workflows, and resolved a critical pre-production latency issue by redesigning serialization/storage. Also built Python-based integrations across CAD/CAE tools and cloud material databases using an XML data model, with a strong interest in digital twins and real-to-sim/sim-to-real robotics workflows.”

“Researcher from the University of South Dakota who built a production medical RAG system to help interpret model predictions by retrieving relevant clinical notes and medical literature, overcoming retrieval accuracy and imaging-dataset challenges through semantic chunking and metadata-driven indexing. Also has hands-on orchestration experience with Airflow and Azure Data Factory, plus a pragmatic approach to LLM evaluation and stakeholder-driven iteration.”

“Built a production multi-agent LLM system at Live Nation on Databricks (LangGraph/LangChain) that let venue/event teams ask questions in Slack, auto-generated optimized route schedules, and produced inventory/stocking recommendations from historical SQL data and venue trends. Improved reliability by tightening prompts with strict JSON schemas, providing sample questions/SQL, and adding guardrails plus synthetic/edge-case testing, while iterating with event managers and senior VPs via prototypes and feedback loops.”

“AI/ML engineer who led production deployment of a multimodal (text/video/image) RAG system on GCP using Gemini 2.5 + Vertex AI Vector Search, scaling to 10M+ documents with sub-second latency and +40% retrieval accuracy. Strong MLOps/orchestration background (Kubernetes, CI/CD, Airflow, MLflow) with proven impact on reliability (75% fewer incidents) and deployment speed (92% faster), plus experience delivering explainable ML (XGBoost + SHAP + Tableau) to non-technical retail stakeholders.”

“Early-stage engineer with hands-on embedded prototyping experience (Arduino/Raspberry Pi) who helped build an award-winning smart glasses project enabling phone notifications via Bluetooth. Strong computer vision performance optimization background, including accelerating 120 FPS inference by moving from TensorFlow to PyTorch and deploying through ONNX + TensorRT quantization, plus Docker-based GPU deployment and CI/ML practices.”