Vetted JWT Professionals

“LLM workflow builder who has deployed a personalized GPT experience (including Delphi AI-based knowledge ingestion) and built a LangChain/LangGraph job-aggregation pipeline that ingests, normalizes/dedupes, filters, then uses an LLM to rank and summarize matches. Emphasizes production reliability with structured outputs, retries/fallbacks, metric-driven evaluation, logging/prompt versioning, and A/B testing, and collaborates with non-technical stakeholders through demo-driven iteration.”

“Built and production-deployed a Streamlit-based PDF RAG chatbot using LangChain (FAISS, embeddings, prompt templates) and OpenAI, optimizing Streamlit’s stateless behavior by caching vector DB + chat history to cut latency and API cost. Demonstrates a rigorous evaluation mindset (gold datasets, unit tests, LLM-as-judge, groundedness KPIs) and has experience communicating privacy/accuracy safeguards (RBAC, data masking, citations) to a non-technical client at Kalven Technologies.”

“Software engineer who builds workflow-centric products end-to-end, including a customer-facing module on the Trident AI content platform and an internal content workflow tool adopted as the default process. Strong in TypeScript/React + FastAPI architectures and in scaling event-driven microservices with RabbitMQ, emphasizing reliability (idempotency, DLQs) and observability (correlation IDs) to reduce outages and debugging time.”

“Frontend lead for a consumer-facing social platform, owning architecture through release. Built scalable React/TypeScript systems (Redux Toolkit, Remix) with a shared Storybook component library and strong quality gates (CI, Jest/Cypress). Experienced modernizing legacy codebases incrementally with feature flags and shipping major dashboard features with staged rollouts and close QA collaboration.”

“Built and deployed ForensicLLM, a local domain-specific LLaMA-3.1-8B model for digital forensic investigators using RAFT + RAG over 1000+ curated research papers, with citation-aware responses and rigorous evaluation (BERTScore/G-Eval). Deployed via vLLM and Docker and validated through a chatbot survey with 80+ participants; published at DFRWS EU 2025.”

“Software engineer with experience across edtech, live gaming, and an AI document intelligence platform, delivering end-to-end customer-facing features and production backends. Built secure, automated live-session scheduling integrating Zoom and TalentLMS (JWT/RBAC, idempotency, transactions) cutting setup time from ~3 minutes to under 1 minute, and optimized real-time gaming dashboards/APIs with query tuning, caching, and CDN improvements (~60% latency reduction under peak load) on AWS.”

“Backend-leaning full-stack engineer in fintech/payments who shipped an end-to-end Stripe payments + webhook system for a financial microservices platform, emphasizing ledger accuracy via idempotency, transactional writes, retries, and DLQs. Also delivered a real-time React/TypeScript payment status dashboard informed by user interviews, and improved production performance by 35% p95 latency through PostgreSQL tuning and Redis caching on AWS.”

“Product-minded engineer who has owned features end-to-end, including a full onboarding redesign that lifted completion ~25% and a production LLM/RAG report-generation system with strong guardrails (schema-constrained JSON, confidence gating, logging) and an automated eval/regression loop built from real user queries. Also built a scalable research data pipeline ingesting messy PDFs/JSON/CSVs with normalization, idempotent reruns, observability, and cost/latency tradeoffs.”

“Data engineer with experience at Morgan Stanley and Star Health owning production-grade lakehouse pipelines for credit risk and healthcare datasets. Built Azure/Databricks/Delta/Snowflake-based platforms processing millions of records per day with strong data quality, observability (Monte Carlo/Azure Monitor), and reliability practices, plus experience delivering curated data services with performance tuning and backward-compatible versioning.”

“Full-stack engineer with deep startup experience building products from scratch under ambiguous requirements. Delivered a scalable, admin-configurable notification platform (Spring Boot/Java/Kafka) supporting 50+ notification types across 3 channels for 10k+ users, cutting new notification setup to ~5 minutes. Also built a Tinder-meets-LinkedIn job-swiping app (React/TS + Node/Prisma) and has hands-on AWS production ops (ECS/EKS, RDS, CloudWatch) plus multiple third-party integrations (Stripe, QuickBooks, Twilio).”

“Backend/data engineer focused on production AWS systems: builds multi-tenant FastAPI services on ECS behind API Gateway/ALB with serverless orchestration (Lambda, SQS, Step Functions) and strong reliability practices (JWT/JWKS auth, idempotency, backoff retries, structured logging). Also delivers AWS Glue/PySpark ETL pipelines with schema/data-quality controls and has modernized legacy analytics logic into Python with parity validation; improved a key dashboard SQL query from ~12–25s to ~2–3s.”

“Senior backend/data engineer who has built and maintained HIPAA-compliant, real-time clinical FastAPI services on AWS, orchestrating ML/LLM and vector DB calls with strong reliability patterns (auth, timeouts/retries, graceful degradation, idempotency). Also delivered AWS IaC/CI-CD (Terraform/Helm/GitHub Actions) across EKS/Lambda/SageMaker and built Glue/Spark ETL with schema evolution and data quality controls, plus demonstrated large SQL performance wins (15 min to <9 sec) and hands-on incident ownership.”

“Backend/platform engineer who built and evolved a large-scale healthcare document processing system (OCR + LLM orchestration) in Python/FastAPI on Google Cloud (Cloud Run, GCS, Firestore), processing ~1.5M files per batch and tens of millions overall. Emphasizes reliability and operational safety via deterministic IDs, idempotent state machines, strong observability, and self-healing reconciliation, plus disciplined migrations using dual-run validation and incremental rollouts.”

“Unity developer with broad cross-platform experience (HTC Vive VR, iOS/Android, Nintendo Switch, WebGL) who built a near-solo multiplayer AR iOS party game using Photon/PUN and AR Foundation. Demonstrates strong practical networking and performance optimization skills, including lag compensation and client-side shader-based rendering strategies.”

“Built and deployed a "personal second brain" product (CloneMind) with an end-to-end RAG pipeline for retrieving information across PDFs, URLs, images, and audio using Next.js/Node.js/Postgres/Supabase/Redis. Demonstrates strong practical depth in retrieval quality tuning, latency reduction via caching, and stateful orchestration with LangChain/LangGraph, plus experience persuading a non-technical professor stakeholder by shipping a working prototype.”

“Frontend engineer with healthcare product experience who led end-to-end delivery of therapist-facing dashboards and clinical workflows in React + TypeScript, including real-time data and multi-role complexity. Emphasizes scalable feature-based architecture, strong domain typing (discriminated unions/domain layer), and performance techniques (scoped state, selector subscriptions, virtualization) alongside disciplined rollout practices (feature flags, QA, monitoring).”

“Frontend tech lead for a university e-signature platform (Next.js/React/TypeScript) replacing paper-based signing. Built a trustworthy multi-signer PDF signing workflow with backend-as-source-of-truth state handling, strong quality gates (typed contracts, linting, pre-commit, PR reviews), and performance work like Web Workers for heavy PDF operations.”

“Frontend/fullstack lead who inherited a messy psychological app with production issues, drove a rapid stabilization (2–3 weeks) and major performance/architecture overhaul (Redux Toolkit, memoization, caching, lazy loading, CDN offload to S3/CloudFront). Also owns delivery and infrastructure practices (multi-env, Docker, GitHub Actions CI/CD, AWS ECS + load balancing) and led a 1-week POC for an AI-powered trucking management system (app.neblo.ai).”

“Frontend engineer with experience building an orthodontics-focused IoT web product, including a complex React + TypeScript 3D treatment viewer with a layered architecture (data layer plus multiple canvas asset managers). Has applied performance techniques like caching and Web Workers to keep the UI responsive under heavy computation, and shipped monetization features such as payments and coupon/discount flows with structured QA rollout.”

“Backend/data engineer who built an end-to-end real-time stock analytics platform: ingesting multi-source market data via Kafka/APIs, transforming it into dashboard metrics (e.g., Bollinger Bands), and storing in BigQuery/MySQL. Strong DevOps/GitOps experience deploying Python/Node microservices on Kubernetes with Docker/Helm, CI/CD (GitHub Actions/Jenkins), and ArgoCD, plus hands-on troubleshooting and migration work.”

“Backend Python engineer who owned the full backend build of an AI-driven platform for UK golf clubs, including FastAPI microservices, vector search, and a tuned LangChain+Pinecone RAG pipeline focused on cost and hallucination reduction. Experienced deploying Django/FastAPI/Flask stacks on AWS-backed Kubernetes with GitOps/ArgoCD-style delivery, plus executing legacy-to-AWS migrations and building Kafka-based real-time analytics pipelines.”

“Backend/platform engineer who has owned FastAPI microservices for analytics/ML ingestion and driven measurable performance gains (cut latency ~40%). Experienced deploying to AWS (ECS/EKS) with GitOps (GitHub Actions + ArgoCD + Helm), and has executed an on-prem to AWS migration using Terraform with parallel-run cutover and ~30% runtime improvement. Also built Kafka-based real-time user activity streaming with Prometheus/Grafana observability.”

“Full-stack engineer who shipped and owned a production Document Chat feature built with Next.js App Router/TypeScript and a Node/Express RAG backend, including JWT-secured route handlers and streaming responses. Demonstrated strong post-launch ownership by improving latency (~30%) via MongoDB indexing/query optimization and reducing AI costs through caching, backed by profiling with React Profiler and Chrome DevTools.”