Senior Full-Stack AI Engineer with LLM Expertise

Jason Sato

Torrance, CA +1-213-***-**** ***********@*****.***

PROFILE

Senior Full Stack AI Engineer with over 8 years of experience designing and deploying AI-driven web applications. Skilled in React, TypeScript, Python, Node.js, microservices, and cloud-native architectures (AWS, Azure), with deep expertise in LLM integration, retrieval-augmented generation, and event-driven systems. Recently developed an AI meeting assistant and multi-agent recommendation agents that streamlined workflows and improved task accuracy. EDUCATION

Duke University Bachelors, Computer Science Durham, NC Aug 2011 - May 2015 EXPERIENCE

Zocks Senior Software Engineer Sep 2023 - Nov 2025

• Developed an AI meeting assistant that recorded Zoom, Teams, and Meet calls as well as in-person sessions via mobile, used AWS Lambda and S3 to store audio, applied Llama 3 for note generation, drafted follow-up emails, and created CRM tasks-leveraging full stack development practices to streamline audio processing and CRM integration, which significantly reduced manual transcription time and increased task-creation accuracy

• Applied a policy-as-code compliance engine to run pre- and post-meeting checks, enforce retention and attestations, and flag restricted terms; the auditable decision logs enabled faster regulatory reviews and lowered compliance audit effort

• Engineered conversational recommendation agents using a fine-tuned Llama 3 model with retrieval-augmented generation over Pinecone vector stores and a multi-agent debate system built with LangGraph-utilizing non-relational databases for scalable vector storage, improving recommendation relevance for knowledge-intensive tasks

• Orchestrated the design of a decentralized MARL framework with Ray/RLLib and Petting Zoo, resolving credit assignment challenges in cooperative agents by implementing QMIX and MADDPG algorithms alongside custom reward shaping.

• Deployed CRM MCP connectors for Salesforce, Wealthbox, and Redtail with robust token and refresh handling, idempotent writes, and conflict-resolution logic; this ensured reliable data synchronization and reduced user-edit conflicts

• Built conversational recommendation agents using fine-tuned Llama 3 with RAG over vector DBs (Pinecone) and multi-agent debate systems (self-correction via Langgraph) to improve consensus in knowledge-intensive tasks.

• Shipped CRM MCP connectors for Salesforce, Wealthbox, and Redtail with robust token/refresh handling, idempotent writes, and conflict resolution against user edits, resulting in more reliable data sync and reduced integration errors

• Architected and optimized high-performance RESTful APIs utilizing FastAPI with Python and Node.js with TypeScript, applying Redis caching and indexing strategies alongside relational database tuning to improve data integration efficiency by 60,000 rpm and reduce API response times

• Designed and optimized GraphQL backend systems by addressing the N+1 query problem with DataLoader allowing for efficient batching and caching of database queries, which enhanced performance and scalability for complex data-fetching operations.

• Boosted application performance by implementing AWS Elastic Load Balancing within cloud platforms, effectively addressing RPS bottlenecks and mitigating DDoS attacks through automated traffic monitoring and rate limiting

• Resolved concurrency challenges through optimistic locking and the utilization of message queues like AWS SQS-embracing event-driven architectures to improve data integrity and accommodate up to 500 concurrent users without performance degradation

• Crafted a responsive and pixel-perfect website utilizing React/Next.js with TypeScript, optimizing performance through advanced techniques like React Query for efficient data fetching and caching strategies, leading to a 25% increase in conversion rates.

• Engineered high-performance server-side rendered (SSR) applications using Next.js 13 with the app router, significantly enhancing SEO visibility and optimizing routing for a more effective user navigation experience.

• Leveraged Capacitor to bridge web apps with native mobile features, enabling hybrid iOS and Android releases in half the time of separate native builds

• Enhanced DevOps workflows by designing and implementing CI/CD pipelines with Jenkins, Docker, and adhering to best practices such as optimizing Dockerfile layers, leveraging multi-stage builds, and utilizing Docker Hub and AWS ECR caching to reduce image build times.

Amazon Senior AI & Full Stack Developer Feb 2021 - Jul 2023

• Championed the 2-year technical vision for Alexa Subscriptions, aligning 8 product lines and over 50 engineers; the platform empowers all voice-driven subscription funnels (Alexa+ Prime, Kids+, Hey Disney!, Skills) and generates multi-million annual recurring revenue.

• Engineered an automated LLM evaluation pipeline benchmarking over 100 model/prompt variants weekly; this initiative reduced manual validation by 95% and gated IS Alexa+ launches across 20 KPIs.

• Standardized the fine-tuning pathway for IP LLMs, resulting in improvements across 8 conversational KPIs.

• Spearheaded the design of a cross-device content recommender now deployed across 6 voice and screen experiences.

• Mentored 9 engineers, leading to 6 promotions to SE2/SE3 roles; conducted over 70 technical interview loops and trained 5 new interviewers.

• Served as the Alexa on-call incident lead for 10 high-severity events; this role cut MTTR by over 50% and established organization-wide ops reviews, design-review forums, and knowledge-sharing practices at the team level.

• Eliminated 190 ms of user-perceived latency by leveraging parallelization and speculative execution techniques.

• Formulated an automated testing and release strategy, enabling full CI/CD pipelines and replacing manual testing and release procedures with efficient workflows.

• Designed and delivered multimodal (voice and visual) feature discovery capabilities for Echo Show (2nd Gen), improving user discovery experience and increasing feature usage

• Architected and launched a bulk Alexa skill enablement service, facilitating skill bundling products.

• Integrated third-party payment gateways, email services, and social media authentication APIs to expand platform functionality and improve the user experience.

• Designed and launched voice-activated subscription features for the Hey Disney! app using AWS Lex and Node.js, defining JSON data contracts and automating deployment with Jenkins pipelines; the new voice interface enabled hands-free sign-ups, increasing subscription accessibility for users

Slalom Full Stack Developer Feb 2018 - Dec 2020

• Led design and development of large-scale web and mobile applications for enterprise and startup clients using React, Next.js, Node.js, Golang, and Python (FastAPI) with PostgreSQL and Redis, delivering solutions that met client requirements and improved user satisfaction

• Collaborated with product and client teams to translate requirements into scalable architecture diagrams, GraphQL APIs, and AWS deployment pipelines (ECS, Lambda, S3, CloudFront), enabling faster release cycles and smoother deployments

• Engineered event-driven microservices for analytics, notifications, and behavior tracking using Kafka, Redis Streams, and GraphQL federation gateways, increasing system reliability and data-processing throughput

• Developed real-time communication layers (WebSocket, Server-Sent Events, and WebRTC) for live dashboards, chat, and telemetry, significantly reducing latency and enhancing engagement by over 0%.

• Unified front-end codebases by creating a shared React/React Native component library and using monorepo tools (Nx, Turborepo), cutting development cycle time by more than 25%

• Implemented CI/CD pipelines with GitHub Actions and Docker, automating integration tests, staging previews, and facilitating zero-downtime deployments.

• Integrated third-party APIs (Stripe, Firebase, Twilio, Google Maps) and built secure authentication flows with JWT, OAuth 2.0, and AWS Cognito for multi-tenant applications, enabling reliable payments, messaging, and location services for users

• Mentored engineers on clean code practices, TDD workflows, peer review disciplines, and observability best practices, contributing to the standardization of performance and reliability across projects.

• Participated in architecture reviews, hiring panels, and internal governance, shaping Slalom's engineering standards for scalability, testing, and security

Laserfiche Junior Full Stack Developer Jan 2016 - Dec 2017

• Delivered React-based customer dashboard features-including Autoship updates, order tracking, and pet profile management-using JavaScript and collaborating closely with product and UX teams, which increased user engagement on the dashboard

• Migrated legacy services to AWS by containerizing workloads, deploying them on Amazon EKS with Terraform, and building CI/CD pipelines in GitHub Actions, which improved system scalability and reduced deployment time

• Reduced P99 latency across high-volume order and inventory APIs utilizing distributed caching, optimized SQL queries, and performance analysis during the Black Friday and Cyber Monday seasons.

• Created observability dashboards with OpenTelemetry, CloudWatch, and Grafana, giving SRE and Logistics teams real-time visibility into fulfillment delays and platform issues

• Integrated machine-learning recommendation endpoints built with Llama 3 and Hugging Face into customer-facing features, coordinating with data-engineering teams and consuming internal personalization APIs, which enhanced product recommendations for users

SKILLS

• AI/ML: LLM Development & Fine-Tuning, RAG, Langchain, Langgraph, Langbase, LangSmith, Hugging Face, Autogen, CrewAI, DSPy, Open AI, Llama 3, PyTorch, Tensorflow, Ray, MLflow, Pinecone, pgvector, FAISS, Multi agent system, Prompt Engineering

& Evaluation, SageMaker, GCP Vertex AL, CUDA

• Languages & Runtime: JavaScript (ES6+), TypeScript, Python, Node.js, Golang, Java (JVM), C#, (.NET), C++, Rust, SQL-

, Bash/Shell/PowerShell, YAML/JSON/Protobuf, GraphQL, CUDA, Julia, WebAssembly (WASM), Ray/Dask, Hugging Face Inference/OpenAI/VLLMruntimes

• Backend & API: Microservices & Distributed Systems, Rest, GraphQL, gRPC, Node.js (Express, NestJS), Python (Flask, FastAPI, Django), Golang(Gin, Fiber), .NET Core/Java Spring Boot, OAuth2, JWT, SSO, RBAC, ABAC, Prisma, TypeORM, SQLAlchemy, EF, Gorm, Redis, Kafka, RabbitMQ, AWS SQS, Websocket, WebRTC, SSE, Pub/Sub, AWS API gateway, NGINX, Kong, Cloudflare, Full Stack Development, Event-driven Architectures, Relational Databases, Non-relational Databases

• DevOps: Terraform, AWS CDK, CloudFormation, Ansible AWS (ECS, Fargate, Lambda, S3, RDS, CloudWatch, EventBridge), GCP & Azure, CI/CD, Github Actions, Jenkins, GitLab CI, Docker, Kubernetes, Prometheus/Grafana, ELK, OpenTelemetry, CloudWatch, SLO/SLA/SLIDesign, VPC & Networking, VPN, Zero-Trust, Auto-Scaling, Cloud Platforms

• Frontend: JavaScript, TypeScript, React/Next.js, Redux, React Query, SWR, TTI, LCP, CLS, SSR, SSG, SEO, Tailwind CSS, Styled-Component, MUI, Figma, Motion, D3.js, Chart.js, Webpack, Vite, Angular/Vue

• Testing: TDD, BDD, Pytest/unittest (Python), Jest/Mocha/Vitest, xUnit/Nunit, Cypress, Selenium, Playwright, Model EvaluationPipelines, Prompt Evaluation, Pandera, k6, Locust, JMeter, OWSAP ZAP

Contact this candidate