Vetted Research Assistants

“LLM/agent engineer who built a production code-generation agent at Corvic AI that lets non-technical users query CSV/tabular data in natural language by generating and executing Python. Focused on making LLM systems reliable and scalable via schema-aware validation, sandboxed execution-feedback retries, prompt caching/embeddings, async execution, and high-throughput data processing with Polars; also partnered with Adobe product/marketing to ship brand-aligned AI content generation for email and push notifications.”

“Software-focused candidate who built a data monitoring pipeline during a hedge fund internship, integrating real databases and an email API to notify teams when data was ready. Comfortable working through legacy/scrappy code and uses LLMs to accelerate comprehension and delivery, with an emphasis on thorough testing and clear communication with stakeholders/customers.”

“ML/NLP engineer with experience at NVIDIA and Cruise building production-grade AI systems across genomics/biomedical research and autonomous vehicle data. Has delivered multimodal LLM pipelines, large-scale entity resolution, and hybrid semantic search (BERT embeddings + FAISS + Elasticsearch), with measurable impact (≈40% accuracy/retrieval gains; ≈30% data consistency improvement) and strong MLOps practices (Kubernetes, CI/CD, MLflow, Prometheus/Grafana).”

“CMU robotics PhD/PhD researcher and former CMU Robotics Club project lead who built a novel Bayes-filter-based system to localize within music so robotic instruments can follow a human’s tempo in real time. Also works on simulation-heavy multi-agent vehicle routing with traffic-signal scheduling, optimizing for real-time performance via profiling, multithreading, and neural-network surrogates for signal control.”

“Software engineering intern who built an internal AI-agent automation using the Gemini API to reduce manual CRM data entry, iterating prompts closely with analysts to address precision concerns. Also worked on a medical image-diagnostics LLM project involving fine-tuning and benchmarking multiple model approaches, and has quant/sales-trading experience building automated pricers for complex options and persuading sales teams to adopt them with ROI-focused metrics.”

“Bain consultant with medtech spin-off/NewCo operating model experience, driving cross-functional workflow optimization, headcount planning, and cost reduction through scenario modeling and executive alignment. Currently on externship at Mediamint, where they built a centralized, standardized pitch-collateral repository and operating cadence to reduce exec time spent on decks and improve GTM consistency.”

“Former Special Assistant at the National Security Council with experience supporting senior federal executives and handling national-security-sensitive information. Helped stand up and standardize operations for a large-scale refugee resettlement effort (60,000 people), creating an executive-driven exception/escalation process and partnering with dev and data teams to prioritize agile sprint work and improve reporting accuracy.”

“P&G operator who is also building and selling an AI receptionist (voice agent) SaaS for healthcare/service clinics, using EHR + calendar API compatibility to target accounts and letting the Voice AI run parts of the demo to prove value. Has already closed and deployed to two clients in the last two months, with production impact via reduced front-desk overhead and automated scheduling/FAQs, and brings a structured, scalable deployment/process mindset from global WMS rollouts.”

“Embedded/robotics software engineer with Hyundai Motors experience who owned an AI-driven perception validation pipeline using a Transformer-based approach to generate stable synthetic in-cabin audio for autonomy/ASR testing, cutting downstream testing time by 50%+. Has hands-on ROS integration (IMU sensor streaming, inference, control nodes), MQTT-based distributed messaging, and cloud/container deployment experience (Docker, Node/Express, AWS, CI/CD).”

“Built and shipped a production LLM-powered medical scribe that generates structured clinical visit summaries using RAG, strict JSON schemas, and post-generation validation to reduce hallucinations. Experienced in making LLM workflows deterministic and observable (structured logging/metrics/tracing) and in evaluation-driven iteration with metrics like schema pass rate and edit rate; collaborated closely with clinicians and policy stakeholders at Scale AI to drive adoption.”