Full Stack Engineer – AI & Distributed Systems

Overview Our client is seeking a highly skilled Full Stack Engineer with deep AI engineering experience to design, build, and scale next-generation intelligent applications used globally by enterprises and end-users. This role is ideal for an engineer who combines backend expertise, frontend excellence, and hands-on AI/ML engineering capabilities—comfortable building everything from distributed microservices to inference pipelines to highly polished UI surfaces. You will work across the entire stack: • AI model integration & LLM orchestration • Vector search & embedding pipelines • Scalable microservices • Data processing and feature engineering • Frontend web app architecture • Cloud-native infrastructure (Kubernetes, serverless, GPU-backed systems) This role will partner closely with product, design, data science, and platform engineering to deliver intelligent, high-performance systems that power the company’s AI-driven suite. Key Responsibilities Full Stack Architecture & System Design • Design and build end-to-end application architectures spanning backend microservices, frontend UI layers, and machine learning inference paths. • Architect data workflows for: • LLM prompting, chaining, and agent execution • Embedding generation and vector retrieval • Streaming and event-driven services (Kafka, Pub/Sub) • Implement scalable APIs and backend services using Node.js, Python (FastAPI / Flask), Go, or Java. • Own technical design documents, architectural reviews, RFCs, and cross-team engineering alignment. Backend Engineering & Distributed Systems • Build high-throughput distributed services with microservice patterns (gRPC, REST, event-driven). • Implement AI workflow orchestration and model-serving endpoints for LLMs, fine-tuned models, and multi-model routing. • Use distributed caching, queueing, and pub-sub systems for low-latency AI applications. • Optimize performance across compute, memory, concurrency, and horizontal scalability. • Implement robust testing frameworks across unit, integration, load, and performance layers. Tech examples may include: Node.js, Python, Go, Redis, Kafka, Postgres, MongoDB, Elasticsearch, gRPC, Docker, Kubernetes, Terraform. AI Engineering & Machine Learning Systems • Build AI-powered features using: • LLMs (OpenAI, Anthropic, Mistral, Llama) • Embedding models (text-embedding, multi-modal) • Vector databases (Pinecone, Weaviate, FAISS, pgvector) • Model-serving frameworks (TensorRT, ONNX Runtime, Triton Inference Server) • Develop pipelines for: • Document chunking • Embedding generation • Retrieval-augmented generation (RAG) • Prompt optimization and evaluation • Use AI tools/frameworks such as LangChain, LlamaIndex, HuggingFace Transformers. Frontend Engineering & User Experience • Build intuitive, high-performance web applications using: • React, Next.js, TypeScript • Tailwind, MUI, or custom design systems • GraphQL/REST/GRPC clients • WebSockets, SSE for real-time interactions • Implement AI-native UX patterns (chat interfaces, agent dashboards, AI copilots, model results visualization). • Collaborate with design and product to deliver refined, responsive experiences across web and mobile browsers. Cloud Infrastructure, DevOps & Observability • Deploy workloads on AWS, GCP, or Azure, including GPU-backed environments for inference. • Build CI/CD pipelines (GitHub Actions, ArgoCD, GitLab CI) to safely ship code multiple times per day. • Use infrastructure-as-code (Terraform, Helm) to manage cloud resources. • Instrument monitoring and observability (Prometheus, Grafana, Datadog, OpenTelemetry). • Optimize cloud costs across compute, storage, embeddings, and AI inference. Security, Compliance & AI Governance • Apply secure coding best practices across backend and frontend systems. • Implement guardrails and governance for AI systems: • prompt injection mitigation • model hallucination detection • safe output filtering • user data privacy & PII redaction • Collaborate with security teams on: • IAM principles • Role-based access control • API authentication & authorization • Data encryption (in transit & at rest) Cross-Functional Collaboration • Work closely with: • Product to refine AI capabilities and refine user workflows • Data Science & ML on model evaluation, tuning, and feature ideation • Design on AI-first UX patterns • Platform Engineering on scalable pipeline architecture • Participate in sprint planning, architecture reviews, incident response, and release planning. Qualifications • 7–12+ years of professional engineering experience across backend + full stack development. • Strong proficiency in JavaScript/TypeScript, Python, or Go. • Hands-on experience with LLMs, embeddings, vector databases, and AI/ML pipelines. • Strong knowledge of modern web development: React/Next.js, TypeScript, state management patterns. • Experience with distributed systems, microservices, event-driven architectures. • Proficiency with relational and NoSQL data stores (PostgreSQL, Redis, MongoDB, Elasticsearch). • Experience deploying and scaling systems in AWS/GCP/Azure environments. • Strong grasp of DevOps, container orchestration (Kubernetes), and CI/CD pipelines. • Experience working in scaling environments (500–2,000+ employee tech orgs preferred). • Bachelor’s degree in Computer Science or related field (Master’s preferred). Leadership Attributes • Deep technical curiosity: passionate about AI, distributed systems, and modern full stack architectures. • End-to-end owner: comfortable owning entire features from backend logic to frontend UI. • High craftsmanship: cares deeply about performance, structure, testing, and reliability. • Innovative builder: brings creativity to solving complex engineering and AI challenges. • Collaborative partner: communicates clearly, works cross-functionally, and elevates team engineering maturity. • Strategic problem-solver: aligns engineering decisions with product goals and long-term system health. Why This Role This is a chance to build AI-native applications inside a fast-scaling SaaS/AI company—shaping the foundation of intelligent products reaching millions of users. You’ll own high-impact features, influence architectural strategy, and build sophisticated systems at the frontier of modern engineering: LLM integration, multi-agent systems, real-time inference, distributed pipelines, and full stack product engineering. If you're a full stack engineer who thrives on technical depth, AI innovation, and end-to-end product creation, this role is a career-defining opportunity.