Vetted NumPy Professionals

“Built end-to-end AI features across both fitness and insurance domains, including a full-stack personalized workout recommendation system and a production RAG-based insurance QA assistant at Relevance Labs. Stands out for combining backend/distributed systems skills with practical LLM architecture, evaluation, and risk-aware human-in-the-loop design; notably reduced unnecessary LLM calls by 40% while improving latency and answer reliability.”

“Built and productionized an LLM-powered clinical assistant at a healthcare startup, re-architecting a prototype into a robust RAG system on AWS with guardrails, citations, monitoring, and automated tests for clinical reliability. Works closely with clinicians to convert workflow feedback into evaluation criteria and iterative system improvements, and has hands-on experience debugging agentic systems in real time (including during live client demos).”

“Backend engineer with hands-on experience building Flask REST APIs (auth, CRUD, S3 media uploads) and driving measurable Postgres/SQLAlchemy performance gains (p95 reduced to 200–400ms by eliminating N+1s and switching to keyset pagination). Implemented multi-tenant isolation with strict tenant scoping plus Postgres RLS, and built an OpenAI-powered quiz generation pipeline using queued workers, structured JSON outputs, and Celery/Redis optimizations to stabilize high-throughput workloads.”

“CMU candidate with hands-on experience taking LLM concepts from research prototypes toward production-ready designs (structured outputs, guardrails, failure-scenario evaluation). Also partnered with sales/customer teams at Mazecare to drive adoption with Dontia Alliance (largest dental clinic chain in Singapore) and engaged Singapore government stakeholders, bridging clinical workflow needs with IT security/integration concerns.”

“Built and deployed an on-prem, HIPAA-compliant LLM pipeline for oncology-focused clinical note generation and decision support, emphasizing grounded differential diagnosis and explainable reasoning via RAG to reduce hallucinations. Also created a LangGraph-based multi-agent academic paper search system integrating Tavily, arXiv, and Semantic Scholar with an orchestrator that routes tasks to specialized sub-agents.”

“Cloud infrastructure/product engineer with end-to-end ownership of cloud-native storage/observability products, including taking an internal CMS to Google Cloud Marketplace and scaling to ~40,000 deployments. Strong in Kubernetes-based platforms (Operators, microservices, RabbitMQ) and performance/scalability work (e.g., 200% cluster capacity increase) plus internal tooling that materially improved SRE/QA debugging and release velocity.”

“Sourcing/procurement-focused candidate who owned vendor selection and risk planning for an IoT pressure/temperature gauge prototype, partnering with a procurement expert on negotiations. Demonstrates strong operations/process mindset by fixing a sales-to-production handover bottleneck with a simple checklist and managing milestones via master trackers and RACI.”

“Built a production LLM-powered RAG agent for healthcare/insurance operations that retrieves and summarizes patient medical documents with grounded citations, scaling to ~4.5M records. Addressed medical shorthand and terminology by fine-tuning ~120 lightweight DistilBERT models by specialty and validating entities against SNOMED/RxNorm, while using SHAP/LIME and human-in-the-loop review to make decisions explainable to stakeholders.”

“Data/analytics professional with experience across manufacturing and enterprise environments (Wisconsin School of Business project with CNH Industrial; roles/projects at Ascensia Technologies, S&C, and Adobe). Has hands-on work combining warranty/lifecycle tables with technician free-text notes using TF-IDF + tree models (XGBoost/Random Forest), and deep experience in entity resolution/reconciliation across mismatched financial systems using Python/SQL and fuzzy matching, with production-grade pipeline practices in Azure Data Factory/Databricks.”

“ML/NLP practitioner working across healthcare and business/finance use cases: currently fine-tuning a domain-specific Llama 3.1 model for safe reasoning over EHRs/clinical notes using RAG + RL/DPO and RAGAS-based evaluation. Has built UMLS-driven entity normalization pipelines with quantified quality gains and developed embedding/vector-DB systems (FAISS) for semantic matching and forecasting/recommendation applications at Aurora AI and Banxico.”

“Robotics software engineer with hands-on experience building a dual-arm (Kawasaki duAro) Cranfield assembly task-planning and motion-planning stack in ROS/MoveIt, using PDDL + behavior trees and OMPL for collision-free execution. Improved tight-tolerance insertions by integrating RGB-D visual servoing into the task planner loop, and also built an LLM-driven navigation pipeline with ORBSLAM3 for natural-language command parsing and real-time replanning.”

“Full-stack engineer building real-time internal banking operations dashboards (Java/Spring Boot microservices + React/TypeScript) with Kafka-based streaming and post-launch performance optimizations. Also shipped a production internal AI support assistant using RAG (Confluence/PDF/support docs ingestion, embeddings + vector DB retrieval) with guardrails, evaluation loops, and observability to reduce hallucinations and prevent regressions.”

Vamshikrishna Bandi

Screened

Senior AI/ML Engineer specializing in Generative AI and agentic multi-agent systems

6y exp

“Built and shipped a production LLM-powered multi-agent RAG system to automate complex internal support workflows, integrating tool execution (SQL/APIs) with validation guardrails to reduce hallucinations. Optimized for real-world latency and cost via model routing, caching, and async parallel tool calls, and enforced reliability with CI-gated golden test sets derived from anonymized production queries.”

Praveen Nutulapati

Screened

Mid-level Generative AI Engineer specializing in LLM fine-tuning, RAG, and agentic systems

New York, NY6y exp

“Built and deployed a production multi-agent RAG system at JPMorgan Chase to automate regulated credit analysis and compliance clause discovery across large internal policy/document libraries. Implemented LangGraph-based supervisor orchestration with structured state management (Azure OpenAI) to support long-running, resumable workflows, plus hybrid retrieval + re-ranking and guardrails for reliability. Strong at evaluation/observability (trace logging, LLM-judge, HITL) and at communicating results to non-technical stakeholders via Power BI embeds and Streamlit prototypes.”

“End-to-end deployment owner for Oracle document delivery/print services in a hospital-like production environment, focused on reliability/performance at scale (thousands of systems). Also describes implementing event-driven RAG/agentic LLM workflows with attention to embeddings/index consistency, latency, and measurable improvements in response relevance and operational efficiency.”

“Candidate combines fraud analytics experience at Citi with a clinical AI capstone involving reproducible ML pipelines for imaging and notes data. They stand out for turning messy, high-volume data into decision-ready reporting, automating evaluation workflows, and translating analytics into operational impact—from fraud rule changes to retention metric adoption.”

Sirisha Maddikunta

Screened

Mid-level Generative AI Engineer specializing in enterprise LLM and healthcare AI solutions

O Fallon, MO6y exp

“Built and owned an end-to-end LLM-powered fraud investigation assistant that automated case summaries and risk analysis, cutting analyst investigation/documentation time by 40%. Stands out for translating RAG concepts into a production-grade internal platform with strong evaluation, monitoring, and reusable Python service architecture that improved both analyst trust and engineering velocity.”

“ML engineer with production experience at PayPal and Flipkart, owning high-scale systems across fraud detection, recommendations, and LLM tooling. Stands out for combining strong modeling judgment with practical platform engineering, delivering measurable impact like 22% fewer fraud false positives, 18% CTR lift, 40% less LLM manual review, and 30% faster redeployments.”

“Full-stack engineer with hands-on experience shipping operational products in inventory and production management, spanning React/TypeScript frontends and Python, Node.js, and Java/Spring Boot backends. Particularly strong in making complex systems usable and reliable in production, including AI-powered anomaly detection with fallback logic, observability, and user-friendly alerting for non-technical operations teams.”

Adam Sandler

Screened

Senior Full-Stack Engineer specializing in Python web platforms

7y exp

“Full-stack engineer with strong Python and React/TypeScript experience who has worked in lean startup environments on B2B SaaS hiring platforms. Most notably, they drove redesign work on developer search and matching systems at G2i, combining product collaboration, backend architecture, and database/query optimization to improve match quality and keep search responses around 100ms at scale.”

“MSR robotics candidate who led a 4-person project building a ROS2 MoveIt wrapper for a Franka Emika arm and integrating a RealSense-based vision pipeline for color-based object tracking/sorting. Also building a quadruped with ROS on Raspberry Pi, bridging ROS commands through a motor driver to TTL-controlled motors, and expanding from Python ROS development into C++ for navigation/LiDAR/SLAM work on TurtleBot3.”

“Software engineer focused on reliability and scalable systems: built React/TypeScript dashboards backed by Java/Spring Boot APIs and designed Kafka-based microservices with strong contract/versioning discipline. Known for shipping incremental improvements with tight feedback loops and for creating internal observability tools that streamline on-call and incident diagnosis under high-traffic conditions.”