Vetted GitHub Professionals

“Robotics-focused engineer with hands-on projects ranging from a solo Dobot Magician Lite tic-tac-toe system (computer vision + minimax) to integrating an LLM with a Dobot arm for real-time pick-and-place via structured action outputs and validation. Also brings prior full-time DevOps experience (Docker/Kubernetes and CI/CD) and has used ROS/Gazebo for simulation work, including exploring improvements to crowd-aware navigation using human-trajectory datasets.”

“Built and deployed a production LLM-powered workflow assistant that automated internal marketing/production business tasks (document summarization, repeated Q&A, status updates). Demonstrates end-to-end applied LLM engineering: modular RAG architecture, hallucination/latency mitigation, automated evals to prevent prompt regressions, and Azure-based orchestration (Functions/Logic Apps) with monitoring and controlled rollouts.”

“Backend/data engineer focused on production-grade Python microservices and AWS platforms, including a hybrid Lambda + ECS Fargate architecture managed with Terraform and CI/CD. Has hands-on reliability experience (JWT/OAuth, timeouts, retries, centralized error classification) and built AWS Glue/PySpark ETL pipelines consolidating PostgreSQL/RDS, MongoDB, and S3 sources into curated partitioned Parquet datasets. Demonstrated measurable SQL tuning impact (8 minutes to 25 seconds) and disciplined legacy-to-modern migrations with parity validation and UAT sign-off.”

“Built and deployed AcademiQ Ai, a production LLM-based teaching assistant using GPT/BERT with RAG (LangChain + Pinecone) to handle large student notes and generate adaptive explanations/quizzes. Demonstrated measurable retrieval-quality gains (18% precision improvement, 22% less irrelevant context) by tuning similarity thresholds and chunking based on user satisfaction signals. Also orchestrated terabyte-scale, real-time demand forecasting pipelines using Airflow and Kubeflow on GCP with strong monitoring, shadow deployment, and feedback-loop practices.”

“Full-stack engineer who builds TypeScript/React SPAs on Python (Flask/FastAPI) backends and has hands-on experience integrating AI components (Azure OpenAI, LangChain, vector databases) into user workflows. Has built internal AI-enabled dashboards/search tools for analysts and business users, emphasizing typed API contracts, CI/CD-driven quality, and microservices reliability patterns (monitoring, retries, idempotency) at scale.”

“LLM/agentic systems engineer who built a production "Agentic AI Diagnostic Assistant" for network engineers, using a multi-agent Llama 2 + LangChain architecture with RAG over telemetry/incident data in DynamoDB and confidence-based deferrals to reduce hallucinations. Also has strong MLOps/orchestration experience (Airflow, EventBridge, Spark, Docker, SageMaker/ECS) at multi-terabyte/day scale and delivered multilingual NLP analytics (fine-tuned BERT/spaCy) for support operations through hands-on stakeholder workshops.”

“Software engineer/product owner experience at UnitedHealth Group owning a high-volume claims eligibility console end-to-end (React/TypeScript + Spring Boot microservices) processing 1M+ transactions/day. Strong in event-driven architecture (Kafka/RabbitMQ), HIPAA-aligned security (OAuth/JWT/RBAC), and building internal observability tools that improve incident triage and production reliability.”

“Backend/platform-focused Python engineer who has owned FastAPI services with Postgres/SQLAlchemy and production-grade auth (JWT + RBAC). Experienced deploying and operating microservices on Kubernetes with GitOps (ArgoCD), HPA tuning, and Prometheus/Grafana monitoring, plus hands-on cloud-to-on-prem migrations and Kafka-based real-time streaming pipelines.”

“Backend/DevOps-leaning engineer with trading/financial systems experience (AIG), focused on reliability: built Python automated test suites to ~95% coverage and integrated them into CI/CD. Has hands-on Kubernetes microservices deployment with GitOps (ArgoCD), plus experience supporting cloud-to-on-prem migrations and building real-time streaming pipelines resilient to spikes and data loss.”

“Built a production internal LLM/RAG assistant at CVS Health to cut time spent searching long policy and clinical guideline PDFs, combining fine-tuned BERT/GPT models with FAISS retrieval and a FastAPI service on AWS. Demonstrates strong real-world reliability work (document cleanup, hallucination controls, monitoring/drift tracking with MLflow) and close collaboration with non-technical clinical operations teams via demos and feedback-driven iteration.”

“GenAI/LLM engineer who recently built a production compliance assistant at State Farm for KYC/AML and regulatory teams, using AWS Bedrock + LangChain with Textract/Lambda pipelines to extract fields, tag risk, and summarize long documents. Implemented RAG, strict structured outputs, and human-in-the-loop guardrails, and reports automating ~80% of documentation work while reducing review time by ~40%.”

“Built a production "appeals co-pilot" for a healthcare claims appeals team, combining an XGBoost/logistic ranking model with a Python/LangChain RAG stack (FAISS + Mistral 7B) to surface high-probability appeal wins and speed policy-grounded drafting. Emphasizes reliability and trust: hybrid retrieval with metadata routing, citation/eval scripts, guardrails, and an explainability layer that non-technical stakeholders could understand and override.”

“Data/ML practitioner with experience at UnitedHealth Group building a fraud claims detection solution combining structured claims data and unstructured notes, validated with compliance stakeholders to improve actionable accuracy. Also applied embeddings, vector databases, and fine-tuned language models in a Bank of America capstone to detect threats/anomalies in financial documents, with production-minded Python ETL workflows using Airflow.”

“Backend engineer with fintech/banking experience (Fifth Third Bank) who built a production payment and reconciliation microservice stack on AWS (Java, PostgreSQL/MySQL, DynamoDB, Kafka) handling thousands of daily transactions and solved real-world reliability issues like duplicate processing and peak latency. Also shipped an LLM-powered ops investigation feature with structured prompt flows, validated internal data integration, and strong guardrails plus human-in-the-loop escalation.”

“Backend-leaning full-stack engineer who has shipped production-critical data/reporting features at Walmart and built an end-to-end workflow automation product (FastAPI + React/TypeScript + PostgreSQL) deployed on AWS. Strong in performance/reliability engineering (parallel ETL, batch DB operations, indexing via EXPLAIN ANALYZE), secure API design (JWT/RBAC), and pragmatic incident-driven scaling (separating workers from API layer).”

“Full-stack engineer with hands-on ownership of real-time, Kafka-driven systems in production, spanning React/TypeScript frontends, Spring Boot/Node backends, and AWS (EKS/ECS/EC2) operations. Notable for modernizing legacy batch workflows into event-driven architectures with measurable impact (35% faster risk calculations, 30% better accuracy) and scaling to 2x volume using reliability patterns like idempotency, retries, and staged rollouts.”

“Backend/full-stack engineer with finance domain experience (State Street) who built and shipped a Kafka-based real-time trade validation system handling 50k+ trades/sec and cut latency by 42%. Also delivered real-time React dashboards (Redux Toolkit/React Query/WebSockets) and operates AWS EKS microservices with GitOps/ArgoCD; has built a FastAPI + LangChain/GPT-4 intelligent document processing service with JWT/RBAC.”

“Software engineer with experience at Freddie Mac shipping a production workflow tracking and daily summary dashboard that replaced spreadsheet/email-based operational processes. Worked across frontend (React/JavaScript), backend (Java), Oracle relational data, and CI/CD, with emphasis on stakeholder collaboration and post-deploy testing/monitoring/performance tuning.”

“QA automation engineer who owned an end-to-end test suite for a financial payments application, building cross-layer E2E coverage (UI/API/DB) and integrating it into CI with smoke-on-commit and nightly regression. Caught high-impact issues including duplicate payments caused by missing idempotency in backend retry logic and an RBAC authorization gap, and has hands-on experience stabilizing flaky Cypress tests via network-call synchronization.”

“Full-stack engineer with ~3.5 years of Java Spring Boot and React experience who built an end-to-end banking transaction platform using microservices, Kafka streaming, AWS RDS, and Dockerized CI/CD. Demonstrates strong performance and reliability engineering (async processing, DLQ/retries, idempotency, caching) plus secure cloud deployment practices; has also worked across banking, healthcare, and insurance domains.”

“Backend/full-stack engineer who has owned production retail and order/inventory systems end-to-end, using Spring Boot microservices with Kafka event-driven workflows. Strong in production correctness patterns (idempotency, retries/DLQs, schema versioning) plus observability (Prometheus/Grafana) and developer-facing API design (Swagger, OAuth2/JWT, versioning/deprecation). Also built TypeScript/React SPAs and cited ~40% UI performance improvement.”

“Engineering leader focused on developer platforms and identity: led a 5-person team building a multi-tenant IAM framework extending Duende IdentityServer, including governance, API standards, and multi-language SDKs. Drove major API architecture improvements by introducing GraphQL alongside REST, cutting client calls from 4 to 1 and reducing payload size by 60% within 6 months, with strong emphasis on stability (semver, E2E tests, feature flags, blue-green deploys).”

“IBM Power/AIX engineer with hands-on experience building Oracle RAC environments on Power10 (VIOS, HMC, LPAR/DLPAR, SEA/NPIV) and troubleshooting high-severity production incidents involving SAN/network dependencies. Has led infrastructure refresh and data center consolidation efforts (Power9 rebuilds via mksysb, staged cutovers) and built shell-script automation for monitoring and backup to improve operational stability.”