Hire the Best Common Language Runtime Specialists

I'm a senior software engineer with 15+ years building production systems for Zalo Group and VNG Corp — Vietnam's largest internet platforms, serving millions of users. I design and ship full-stack SaaS products end-to-end: database schema, backend APIs, frontend, and the DevOps/security layer that keeps them running safely in production. What I bring to your project: - Full-stack SaaS delivery — Java/Node.js/Python backends, React/Next.js frontends, PostgreSQL/MySQL/MongoDB/Redis data layers, built for multi-tenant and self-serve products from day one. - AI/LLM engineering — build production AI systems end-to-end: document processing pipelines (OCR, chunking, embeddings), RAG search over vector databases (Qdrant), multi-model LLM gateways (LiteLLM) for cost/latency-aware routing, and async task orchestration (Celery) for long-running AI workflows. - Security & access control — designed and built an internal system that scores and gates employee device/server access based on real-time risk signals (used company-wide at Zalo), plus envelope encryption (HashiCorp Vault, AES-256-GCM) for data-at-rest protection. - Data & analytics platforms — built a Google-Analytics-style tracking system processing traffic from Zalo's entire product suite, plus a content-fingerprinting system for detecting copyrighted music uploads. - DevOps & process — built internal tooling for CI/CD, staff performance tracking, and SDLC process automation used across Zalo's engineering org. - Startup speed — currently building my own AI SaaS platform solo (FastAPI, Celery, Postgres, Qdrant, Next.js), so I move fast, ship MVPs, and think about cost/scale trade-offs like a founder, not just an engineer. I care about clean architecture, clear communication, and shipping things that don't fall over at 2am. If you need someone who can own a feature or a whole product — from schema to deploy, from OCR pipeline to production AI agent — let's talk.

Building an AI model is easy. Building an AI system that remains reliable, scalable, and cost-effective in production is where engineering makes the difference. New to Upwork. Not new to AI engineering. For over 3 years, I've helped startups design, build, and deploy production AI systems, not just proof-of-concepts. I work at the intersection of applied AI and production engineering, focused specifically on production LLM systems, RAG pipelines, AI agents, and the ML infrastructure that keeps them reliable under real traffic. When classical Machine Learning or Deep Learning is the better fit for part of your platform, I engineer those solutions with the same production discipline. I don't believe every problem should be solved with the latest AI trend. My role is to identify the right approach for your startup and build infrastructure that balances performance, scalability, cost, and long-term maintainability. From architecture and model development to backend engineering, deployment, and monitoring, I handle the complete AI engineering lifecycle for your platform. You work with one partner who understands both the AI and the infrastructure required to run LLM, RAG, and AI agent systems successfully in production. ⭐ How I Can Help • Design and build production-ready LLM, RAG, and AI agent systems • Set up ML infrastructure and platforms for production • Develop Machine Learning and Deep Learning solutions where they're the better fit • Design and implement scalable AI APIs and backend systems • Integrate AI agents into your existing platform • Deploy AI systems using modern cloud infrastructure • Optimize AI systems for latency, reliability, scalability, and cost • Implement observability, monitoring, and production maintenance for your AI infrastructure ⭐ Domains I've Worked In Finance & FinTech | Healthcare | Enterprise SaaS | Document Intelligence | Business Process Automation ⭐ Core Technologies Python • FastAPI • Machine Learning • Deep Learning • PyTorch • Lamma.cpp • LLMs • RAG • AI Agents • LangGraph • MCP • MLOps & Infrastructure • MLflow • Docker • Kubernetes • CI/CD • GPU Inference • AWS • Google Cloud • Microsoft Azure ⭐ Why Startups Work With Me ✔ End-to-end AI infrastructure engineering, from architecture to deployment ✔ Production-first LLM, RAG, and AI agent systems designed for long-term scalability ✔ Clean, maintainable, and well-documented code ✔ Strong communication with regular progress updates ✔ Engineering decisions driven by measurable business outcomes, not hype My engineering experience is backed by formal training through the IIT Madras Diploma in Data Science, one of India's leading data science programs, giving me a solid foundation in the math, statistics, and optimization behind the models and infrastructure I build. Whether you're setting up ML infrastructure, building a new LLM or RAG platform, or scaling an AI system already in production, I can help. Let's discuss your project. I'll help you choose the right technical approach, identify potential challenges early, and build production infrastructure that's reliable, scalable, and designed for long-term success.

Most AI agents demo beautifully, then fall apart the first week real customers touch them: confident wrong answers, calls that drop mid-sentence, replies that ignore what the customer already told you. The model was never the hard part. Everything that breaks lives in the seams. I build voice and conversational AI agents that survive that, not demos that shine on a sales call and die in production. Today I run 12 conversational AI agents live in production: they listen, classify intent, answer what's in scope, and hand off to a human the moment they're out of their depth, with memory, dedup, anti-loop guards, and confidence-gated escalation so they don't hallucinate or spam. I've shipped omnichannel support inboxes end to end (Telegram, WhatsApp, Crisp), earned 5 stars on my last delivery, and built a production voice assistant in a high-stakes domain (multi-LLM voice pipeline + MCP tool-calling). Where these agents actually break isn't the model, it's the seams: latency, flaky function-calling, no clean human handoff, no state recovery after a restart. That's my lane. I work natively in Claude (Claude Code, custom MCP servers, the Anthropic API) and voice stacks like Vapi/Retell, Twilio, ElevenLabs/Deepgram, plus LLM function-calling, FastAPI webhooks, and Python. What I won't waste your time on: "AI strategy" decks, ChatGPT wrappers you could build yourself, or a demo that was never built to survive real customers. I quote, scope, ship, and hand off documented code with a runbook. Taipei (GMT+8). Text-first, fluent written English, same-day replies.

✅ 6+ Years of Java Development Experience ⚡ Full-Cycle Backend Development & Architecture ⚡ AI-Powered Development for Faster Delivery & Better Code Quality 👀 Click Invite or Hire for Scalable Java Backend Solutions Looking for a Java Developer who can build scalable backend systems, SaaS platforms, enterprise applications, and cloud-native solutions designed for long-term growth? For 6+ years, I have hands-on experience taking multiple backend systems from zero to production — covering API design, database modeling, AI/LLM integration, payment systems, and server deployment end-to-end. My primary stack is Java and Spring Boot, with a strong focus on building systems that are clean, maintainable, and ready to scale. What I can do for you: 𝐁𝐚𝐜𝐤𝐞𝐧𝐝 𝐀𝐏𝐈 𝐃𝐞𝐯𝐞𝐥𝐨𝐩𝐦𝐞𝐧𝐭 | Java · Spring Boot · Spring MVC · Spring Security · JWT · Design and build RESTful APIs from scratch · Implement authentication & authorization (JWT, Spring Security, role-based access control) · Structure business logic that is clean, testable, and maintainable 𝐀𝐈 & 𝐋𝐋𝐌 𝐈𝐧𝐭𝐞𝐠𝐫𝐚𝐭𝐢𝐨𝐧 | Claude API · OpenAI · Prompt Engineering · Integrate Claude or OpenAI into real product workflows — not just demos · Build multi-turn dialogue flows and connect model outputs to backend logic · AI-powered automation pipelines and event-driven AI workflows 𝐃𝐚𝐭𝐚𝐛𝐚𝐬𝐞 𝐃𝐞𝐬𝐢𝐠𝐧 & 𝐌𝐚𝐧𝐚𝐠𝐞𝐦𝐞𝐧𝐭 | PostgreSQL · MySQL · Redis · Spring Data JPA · Qdrant · Design schemas and data models from scratch · Write complex queries and handle migrations · Performance optimization and caching with Redis · Vector database setup and operations — storing embeddings, similarity search, and retrieval pipelines (Qdrant) 𝐏𝐚𝐲𝐦𝐞𝐧𝐭 & 𝐒𝐮𝐛𝐬𝐜𝐫𝐢𝐩𝐭𝐢𝐨𝐧 𝐒𝐲𝐬𝐭𝐞𝐦𝐬 | Stripe Connect · Webhook · Integrate Stripe — subscription tiers, billing cycles, webhook event handling · Build payout logic and third-party payment flows 𝐒𝐞𝐫𝐯𝐞𝐫 𝐃𝐞𝐩𝐥𝐨𝐲𝐦𝐞𝐧𝐭 & 𝐃𝐞𝐯𝐎𝐩𝐬 | DigitalOcean · Docker · Nginx · CI/CD · Linux · Set up and manage production environments · Docker containerization, Nginx reverse proxy, SSL, CI/CD pipelines 𝐓𝐡𝐢𝐫𝐝-𝐩𝐚𝐫𝐭𝐲 & 𝐖𝐞𝐛𝐡𝐨𝐨𝐤 𝐈𝐧𝐭𝐞𝐠𝐫𝐚𝐭𝐢𝐨𝐧 | FCM · APNs · OAuth · REST · Connect backend to external services via REST APIs or webhooks · Push notifications (FCM / APNs), OAuth, event-driven automation 𝐅𝐫𝐨𝐧𝐭𝐞𝐧𝐝 𝐂𝐨𝐥𝐥𝐚𝐛𝐨𝐫𝐚𝐭𝐢𝐨𝐧 | Vue3 · Nuxt.js · TypeScript · Tailwind CSS · Work alongside frontend teams or handle supporting frontend work independently · Define API contracts, handle CORS, integrate backend services end-to-end I communicate clearly, deliver on schedule, and am comfortable working independently from requirements through to deployment. Feel free to reach out with your project.

Availability: Full-time freelancer, 𝟰𝟬+ hours/week, open to long-term collaborations. I’m a Full-Stack & AI Engineer with 10+ years of experience building web and mobile applications and 3+ years of specialized experience in AI and Large Language Models (LLMs). I design, develop, and deploy production-grade platforms, from scalable SaaS dashboards to AI-powered assistants, RAG systems, and voice agents. I work end-to-end: architecture → backend → frontend → cloud deployment, with a focus on clean code, maintainable systems, and high performance. Over the past few years, I’ve delivered solutions that integrate AI/LLM pipelines, vector search, real-time chat, and voice agents for enterprise and startup clients. 🤖 AI & LLM Expertise - MCP Server Development: Designing and integrating custom MCP servers for AI agents, enabling structured tool usage, external system integrations, database querying, and API orchestration. - Fine-Tuning: Persona creation, Q&A systems, and domain-specific models (medical, legal) using Mistral and Llama 3. - Synthetic Dataset Generation: Streamlining LLM training with high-quality datasets. - Evaluation Frameworks: Assessing LLM performance with custom metrics. - Cloud Deployment: Deploying LLMs on AWS and GCP. - AI Agents & Voice Bots: Proficient with LiveKit, Retail AI, OpenAI. - Open-Source Deployment: Expertise deploying models like vLLM on AWS/GCP/RunPod using SkyPilot. 🛠️ 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗧𝗼𝗼𝗹𝘀 & 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀 ➜ LLM Tools: LangChain, Langsmith, Langfuse , Hugging Face, Transformers. ➜ Vector Databases: Chroma, FAISS, Pinecone, Qdrant , Opensearch ➜ AI Workflows: Flowise AI, LangFlow, StackAI. 🛠️ 𝗙𝘂𝗹𝗹 𝗦𝘁𝗮𝗰𝗸 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗘𝘅𝗽𝗲𝗿𝘁𝗶𝘀𝗲 ➜ Languages & Frameworks: Python, Node.js, ReactJS. ➜ Database Management: MongoDB, MySQL, PostgreSQL , Supabase , FIrebase ➜ Frontend & Backend Integration: Seamlessly connecting APIs and user interfaces. 🌟 𝗔𝗱𝘃𝗮𝗻𝗰𝗲𝗱 𝗦𝗸𝗶𝗹𝗹𝘀 ➜ Open-Source LLMs: Proficiency in LLAMA 3, Mistral 7B, and Mixtral 8x7B. ➜ Prompt Engineering: Expertise in techniques like Chain of Thought, Few-shot Prompting, and Self-Reflection. ➜ Fast Inference: Implementing high-speed solutions with vLLM . 🌟 𝗪𝗵𝘆 𝗖𝗵𝗼𝗼𝘀𝗲 𝗠𝗲? With over 10 years of experience, I deliver scalable, cutting-edge solutions tailored to your project’s needs. Whether it's advanced AI models, MCP server development, LLM optimization, or full-stack development, I ensure top-notch results every time. Let’s collaborate to bring your ideas to life!

Hi! I'm Burak. A professional English-Turkish linguist, AI language trainer, and localization specialist with hands-on experience across global projects. I provide high-quality translation, localization, proofreading, transcription, and LQA services. I have worked with international platforms and organizations such as RWS, Moravia, Crowdgen, Witness Change, Mindy Support, Apple LLM projects, and multiple AI labs as a data annotator, quality rater, and guideline-based evaluator. What I offer EN ↔ TR Translation & Editing Localization (apps, websites, games, marketing) Linguistic QA & Style Guide Compliance Transcription & Subtitle creation (SRT, VTT) AI training & text evaluation (LLM tasks, labeler work) Professional tone & terminology consistency Fast delivery & revision support Strengths Detail-oriented & guideline-focused Tech-savvy (CAT tools, QA tools, Jira, memoQ, Trados) Strong educational background in language & pedagogy Experience in strategy/game content, apps, e-learning, social impact content My priority is to deliver accurate, natural, culturally-fitting language that makes your content shine. Let's work together. Message me to get started! TR Merhaba! Ben Burak. Profesyonel İngilizce-Türkçe çevirmen, lokalizasyon uzmanı ve AI dil eğitmeniyim. Çeviri, lokalizasyon, düzeltme okuması, transkripsiyon ve LQA alanlarında yüksek kaliteli hizmet sunuyorum. RWS, Moravia, Crowdgen, Witness Change, Mindy Support ve Apple LLM projeleri dahil birçok global platformda görev aldım. Hizmetler EN ↔ TR çeviri ve metin düzenleme Uygulama, web sitesi ve oyun lokalizasyonu LQA ve stil rehberi uyumu kontrolü Altyazı & transkripsiyon (SRT, VTT) AI metin değerlendirme ve veri etiketleme Becerilerim Kılavuzlara titizlikle uyma Hızlı ve güvenilir teslimat CAT tools & QA araçları (memoQ, Trados, Jira) Eğitim & dilbilim temelli profesyonel yaklaşım Doğal, akıcı ve kültürel olarak uygun içerik üretmek için buradayım. İş birliği için mesaj bırakabilirsiniz!