Vetted Reinforcement Learning Professionals

“Built and deployed an LLM-powered mental health therapy assistant at AppHealth that segments users by stress level and delivers personalized, non-medical guidance. Implemented healthcare-focused safety guardrails (secondary LLM output filtering) and a multi-agent router workflow validated via statistical tests and therapist review, then scaled training/inference on AWS (EC2/Lambda/DynamoDB) with Kubernetes.”

“Built and deployed a production LLM-powered support assistant for customer support agents using a RAG architecture over internal docs and past tickets, with human-in-the-loop review. Demonstrates strong applied LLM engineering focused on real-world constraints (hallucinations, latency, cost) using routing to smaller models, reranking, caching, and rigorous evaluation/monitoring (offline eval sets, A/B tests, KPI tracking).”

“Internship experience shipping production AI systems: built an end-to-end RAG platform (Python/FastAPI + LangChain/LangGraph + vector search) to answer support questions from unstructured internal docs, with a strong focus on hallucination prevention through confidence gating and rigorous offline/online evaluation. Also delivered an AI-driven personalization/analytics feature using an unsupervised clustering pipeline, iterating with PMs to align statistically strong clusters with actionable business segmentation.”

“Built and deployed a production RAG system for financial/compliance teams using GPT-4, Claude, and local models to retrieve and summarize thousands of internal documents with strong security controls (role-based retrieval, PII masking). Drove significant operational gains (30+ hours/week saved, ~35% productivity lift, ~45% faster responses) and orchestrated end-to-end ingestion/embedding/index refresh pipelines with Airflow, S3, and SageMaker while partnering closely with compliance stakeholders on auditability and traceability.”

“Backend engineer who built and owned an AI-powered financial research product end-to-end, using a typed NestJS/GraphQL backend with LangGraph-style agent routing to produce sourced, structured financial analysis. Emphasizes finance-grade correctness (Zod validation, metric registries, unit/empty-result guardrails) while keeping latency low via batching, caching, and fast token streaming, and has led incremental migrations using strangler/feature-flag/shadow traffic patterns.”

“Robotics/embodied-AI practitioner who built a TurtleBot3 LiDAR-fingerprint localization pipeline end-to-end (autonomous data collection + multi-head NN) achieving ~30 cm error in a 10x10 m space. Also has industry experience at Infineon building large-scale production data/AI pipelines and rapidly fixing a deployed recommendation system by correcting upstream data normalization, improving accuracy by 20%+.”

“Robotics software engineer with hands-on depth across simulation (Isaac Sim, Gazebo, Webots), ROS/ROS2 integration, and real-time embedded control. Led an end-to-end quadruped (12-motor) Isaac Sim build from Fusion 360 CAD-to-URDF through physics tuning to achieve a stable walking gait, and optimized a 5-servo arm by cutting IK compute time by 60%+ using lookup tables to eliminate jitter.”

“Recent UC Riverside master’s graduate focused on uncertainty-aware imitation learning for indoor robot navigation, building a full ROS 2 Humble stack (perception, learned policy, uncertainty estimation) with adaptive speed control. Demonstrated strong real-time robotics debugging and systems skills, achieving 92% autonomous navigation success across 100 trials and improving reliability through uncertainty calibration and SLAM/loop-closure optimization.”

“ML/NLP engineer (Beyond Identity) who built production semantic search and entity-resolution systems over internal security documentation, using LDA + BERT embeddings with FAISS/Pinecone to cut search time by 30%. Also scaled a real-time anomaly detection pipeline to millions of events/day with Spark and AWS Lambda, with strong emphasis on measurable validation (Precision@k, MRR, F1, ARI).”

“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.”

“Robotics software/vision engineer with hands-on experience building motion-tracking systems that fuse camera-based 3D tracking with IMU orientation to reproduce tool motion for automated spray painting. Has implemented ROS nodes/packages for Orbbec camera streaming and SAM3-based segmentation, plus CAN bus coordination between robots and Dockerized deployment for a pick-and-place robotic cell.”

“Backend engineer who built and evolved a gun-parts price tracking platform focused on accurate historical pricing and fast graph-ready APIs. Experienced migrating an Express backend to NestJS incrementally with parallel routing, feature flags, and careful data integrity controls, and has a security-focused approach to API design (JWT/OAuth, RBAC, row-level access via scoped queries).”

“Robotics/ML candidate building an individual pedestrian trajectory forecasting system by adapting a GAN-style Social-GN training architecture from LSTM to a transformer-based AgentFormer design. Also has hands-on embedded robotics experience debugging lane-following behavior on a JetBot by tuning PID control, and uses Docker for reproducible training environments.”

“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/MLOps engineer who has shipped a production RAG-based technical documentation assistant (FastAPI) cutting manual review by 45%, with deep hands-on retrieval optimization in Pinecone/LangChain (HNSW, hybrid + multi-query search, caching). Also brings healthcare domain experience—building Airflow-orchestrated EHR pipelines and delivering FDA-auditability-friendly predictive maintenance solutions using SHAP/LIME explainability surfaced in Power BI.”

“Robotics software architect who built an automated pick-and-place palletizing prototype at BLACK-I-ROBOTICS, spanning perception (multi-RealSense fusion, segmentation, 6D pose, ICP), GPU-accelerated motion planning (MoveIt 2 + NVIDIA CuRobo), grasp generation, and safety (human detection + safe mode). Also brings cloud/CI/CD depth from VERIDIX AI (AWS Cognito/Lambda/ECS and CodePipeline stack) and demonstrated strong debugging chops by reducing outdoor rover EKF drift to ~5 cm via Allan variance-based IMU tuning.”

“LLM/GenAI engineer who built a production AI-powered credit risk policy summarization and compliance alerting platform at HCL Tech, focused on factual accuracy and auditability for a financial client. Implemented a multi-retriever LangChain RAG architecture with citations-only prompting, fallback agents, and human-in-the-loop legal review—cutting manual review time by 35% and scaling to 12 teams.”

“LLM engineer who built and productionized a system to classify GitHub commits (performance vs non-performance) using zero-/few-shot approaches over commit messages and diffs, working at ~5M-record scale on multi-node NVIDIA GPUs. Experienced orchestrating end-to-end LLM pipelines with Airflow and GitHub Actions, and emphasizes reliability via testing, guardrails, and observability while collaborating closely with non-technical product stakeholders.”

“AI/ML practitioner in healthcare/insurance (Blue Cross Blue Shield) who built and deployed a production NLP system to classify patient risk from unstructured clinical notes. Experienced in end-to-end pipeline orchestration (Airflow, AWS Step Functions/Lambda/SageMaker) and real-time optimization (BERT to DistilBERT on AWS GPUs), with strong clinician collaboration to drive adoption.”

“UE5 Blueprint-focused gameplay/system designer who shipped an XR interactive experience (“Echoes of the Moon”), owning interaction logic, progression triggers, state management, and animation syncing through ship. Emphasizes modular component-based architecture with interfaces and data-table-driven tuning, plus strong profiling/optimization skills (refactoring Tick-heavy systems to event-driven) validated through 20–30 user playtests and mobile XR (Android) frame-budget constraints.”

“Robotics software engineer who built a full LiDAR SLAM pipeline from scratch in C++ (ICP, pose graph optimization, loop closures) and validated it quantitatively against ground-truth datasets. Extensive ROS2 experience from academics and an internship building a localization system, plus practical deployment work using Docker across x64 and ARM edge devices; also trained RL policies for TurtleBots in Gazebo.”

“Robotics software engineer with hands-on ROS2 experience building perception-driven navigation for AMRs, integrating YOLO11 + Depth Anything V2 and multi-sensor fusion (LiDAR/RGB-D/IMU) to boost pose accuracy by 30%. Strong in real-time debugging and edge deployment on NVIDIA Jetson (ONNX/CUDA), plus cloud-enabled telemetry (Azure) and simulation-driven testing (Isaac Sim) that cut physical test cycles by 25%.”

“Robotics software candidate whose thesis focused on multi-robot warehouse coordination using MAPPO reinforcement learning, trained in simulation (LBF environment, Isaac Sim/RViz) and deployed onto three real-time robots. Built custom ROS 2 Humble nodes for multi-robot control with namespaces, TF broadcasting, and an RL pipeline integrating LiDAR odometry and camera observations.”