Vetted GitHub Professionals

“LLM engineer who has deployed production RAG systems for regulated document QA (PDFs/knowledge bases), emphasizing grounded answers with citations, RBAC, monitoring, and continuous feedback. Demonstrates deep practical expertise in retrieval quality (semantic chunking, hybrid BM25+embeddings, re-ranking), reliability (guardrails, deterministic workflows), and measurable evaluation (golden sets, log replay, A/B tests) while partnering closely with compliance/operations stakeholders.”

“Lead software engineer (3+ years) who built and scaled an AI product backend at Cosmo AGI from the ground up using FastAPI/Postgres/Redis/vector DB, targeting sub-200ms latency and supporting 1000+ active users. Strong in production-grade security and observability (OAuth/JWT, RBAC, Postgres RLS, Prometheus/Sentry), plus DevOps automation (Docker, GitHub Actions, blue-green deploys) with measurable impact on uptime, incidents, engagement, and deployment speed.”

“Robotics software engineer focused on real-time estimation/control and motion replanning, currently integrating a factor-graph-based estimation/control stack with sampling-based replanning in a ROS environment validated on both MuSHR hardware and MuJoCo simulation. Strong in distributed-system debugging (rosbags/logging, controlled test scenarios) and ROS performance patterns (nodelets, TF/TF2), with prior multi-robot experience from SSL RoboCup using custom UDP protocols.”

“Python/AWS engineer focused on batch-processing and data workflows, including building reusable S3/boto3 utilities with reliability features and IAM-based auth. Has led low-risk legacy modernizations using parity testing plus a month of parallel production runs, and has owned production issues end-to-end (including fixing a client-side Excel macro) while contributing to significant AWS cost reductions (~$10k/month).”

“Worked on Sophia the humanoid robot, building production animation pipelines and enhancing human-robot interaction via perception and behavior orchestration. Experienced in stabilizing noisy perception-driven state transitions and designing smooth, user-centered behavioral flows, collaborating closely with artists, animators, and experience designers to translate creative intent into measurable system behavior.”

“AI/ML practitioner with Northern Trust experience who has shipped production LLM systems (internal support assistant) using RAG, vector databases, orchestration (LangChain/custom pipelines), and rigorous monitoring/feedback loops. Also built AI-driven fraud detection/risk monitoring solutions in a regulated financial environment, emphasizing explainability (SHAP), audit readiness, and stakeholder trust through dashboards and clear communication.”

“At JP Morgan Chase, built and deployed a production LLM-powered RAG knowledge assistant to help fraud investigators and risk analysts quickly navigate regulatory updates and internal policies, reducing investigation delays and compliance risk. Strong focus on secure retrieval (RBAC filtering), reliability (layered testing + observability), and production constraints (latency/SLOs), with Airflow-orchestrated, auditable ML pipelines.”

“LLM/RAG engineer who has built and deployed corporate-scale systems at Novartis and Johnson & Johnson, including a healthcare AI agent that generates day-to-day treatment schedules. Recently handled a high-stakes safety incident (LLM suggesting overdose) by tightening model instructions and validating with ~200 test prompts, and has strong end-to-end data/embedding/vector DB pipeline experience (PySpark, FAISS, Pinecone) plus SME-in-the-loop evaluation (RLHF).”

“Built and shipped a production LLM-powered personalized client engagement assistant in the financial domain, balancing real-time recommendations with strict privacy/compliance requirements. Demonstrates strong MLOps/LLMOps depth (Airflow + MLflow, containerized microservices, drift monitoring) and a privacy-by-design approach validated in collaboration with risk and compliance teams.”

“AI/ML full-stack practitioner in a small-scale manufacturing/lab operations environment who deployed a production ML system to improve blood cell order fulfillment by predicting yield/success from donor characteristics. Experienced building custom multi-agent orchestration (Python, LangChain/LangGraph, MCP) and balancing reliability, data quality constraints, and token/ROI economics while communicating tradeoffs to VP-level business stakeholders.”

“Enterprise platform engineer/product owner who led end-to-end delivery of customer-facing ServiceNow Service Catalog/workflow solutions, emphasizing reliability, security, and fast iteration. Built React/TypeScript portals with Node.js and Spring Boot backends, and improved microservices reliability at scale using Kafka, monitoring, and robust retry/timeout patterns.”

“Backend engineer focused on Python/FastAPI microservices, with hands-on experience deploying to AWS (EKS/ECR) via Jenkins and GitOps-style workflows using ArgoCD. Has built and stabilized real-time Kafka payment-event streaming pipelines and improved production performance under peak load through Redis caching, SQL optimization, and robust retry/DLQ patterns. Also supported phased migrations from on-prem environments to AWS with gradual traffic shifting and monitoring.”

“Built ToolDreamer, a framework for selecting relevant tools for LLM agents by training a retriever on LLM-generated reasoning traces, and has hands-on experience building multi-agent systems in AutoGen (MAG-V) focused on question generation and tool-trajectory verification. Currently works as an AI-guides supervisor at Penn State, regularly communicating AI concepts to non-technical stakeholders.”

“AI/ML engineer with HP experience building and productionizing an LLM-powered document intelligence platform (LangChain + Pinecone) to deliver semantic search and contextual Q&A across millions of enterprise support documents. Demonstrates strong MLOps and scaling expertise (Airflow, Kubernetes autoscaling, Triton GPU inference, monitoring with Prometheus/W&B) plus a structured approach to evaluation (A/B tests, shadow deployments, failover) and effective collaboration with non-technical stakeholders.”

“GenAI/data engineering practitioner with production experience across Equinix, Optum, and Citibank—built an Azure OpenAI (GPT-4) + LangChain document intelligence platform processing 1.5M+ docs/month and a HIPAA-compliant Airflow healthcare pipeline handling 5M+ claims/day. Also delivered a real-time fraud detection + explainability system using LightGBM and a fine-tuned T5 NLG component, improving fraud accuracy by 15%+ while partnering closely with compliance stakeholders.”

“Internship experience building a production RAG+LLM pipeline to map messy card transaction descriptions to merchant brands, including a custom modified-ROUGE evaluation approach for weak/variant ground truth. Improved scalability and cost by moving from a managed LLM endpoint (e.g., Bedrock) to self-hosted vLLM, and orchestrated massive embedding backfills (5,000+ files, 10B+ rows) using an Airflow-triggered SQS + ECS worker architecture with robust retry/DLQ handling.”

“Built a lightweight internal JavaScript analytics tracker capturing user interactions (clicks, page views, custom events) with debounced batching, automatic session tracking, and offline event caching via a localStorage-backed append-only queue. Demonstrates practical performance optimization mindset (profiling, memoization/caching) and React performance tuning.”

“Backend/platform engineer from Fanatics sportsbook core team with deep experience in real-time ingestion systems (Kafka) and high-throughput performance optimization. Delivered an 87% latency reduction on a Java API handling hundreds of thousands of updates per second, and improved reliability of shared internal libraries via deterministic recovery logic, strong testing, and feature-flagged rollouts.”

“Built and deployed a secure, production LLM-based document summarization and risk-highlighting tool for financial auditors, running inside a private Azure environment to protect confidential data. Focused on reliability (hallucination mitigation via retrieval-based prompts and source citations) and validated performance through comparisons to auditor summaries plus a user pilot, cutting review time by about half.”

“Backend-focused Python/Flask engineer who has built authentication/profile services with clean modular architecture (blueprints + service layer) and tuned SQLAlchemy/Postgres for scale using indexing, query rewrites, and pagination. Has production-style integration experience for AI/ML via TensorFlow Serving and OpenAI APIs (batching, rate limiting, caching), plus multi-tenant data isolation and high-throughput background processing with Celery/Redis and idempotent jobs.”

“Built and owned an end-to-end Seat Allocation & Management System at Accenture, replacing a legacy process with a scalable web app used across teams. Deep focus on reliability under concurrency (transactions + unique constraints + idempotent APIs) and on Postgres performance tuning (composite indexes, EXPLAIN ANALYZE), plus post-launch production support and monitoring.”

“Machine learning/NLP engineer who built a production-oriented retrieval-based AI system at Morgan Stanley for healthcare use cases, combining RAG over unstructured patient records with deep-learning medical image segmentation (U-Net/Mask R-CNN). Strong in end-to-end pipelines and MLOps (Spark/MongoDB, AWS SageMaker, CI/CD, monitoring, automated retraining) and in entity resolution/data quality validation for noisy clinical data.”

“Uber engineer who has owned internal products end-to-end across backend (Spring Boot microservices, MySQL) and frontend (React), including performance optimization and secure JWT-based auth. Also shipped a production internal RAG/embeddings LLM support assistant over policy docs and support tickets, with guardrails (confidence thresholds, human review) and an evaluation loop that directly reduced hallucinations.”