Sr. Full - Stack Engineer - AI

As a Senior Full-Stack Engineer, you will build production-grade systems that go well beyond conversational assistants. This role sits at the intersection of software engineering, data engineering, and agentic engineering, building stateful, goal-driven AI systems that can reason, plan, coordinate, and execute complex tasks with appropriate controls. You will collaborate closely with colleagues across product, design, infrastructure, and other application engineers. You will help enforce sound engineering practices and ensure our AI-driven applications remain robust, maintainable, and performant. You must demonstrate a strong understanding of cloud architecture principles.
Responsibilities:
Build High-Quality SPAs: Design, develop, test, and maintain Single Page Applications ranging from experiments to flagship products.
Build High-Quality Backend Systems: Design, develop, test, and maintain backend services and APIs that power AI applications, ensuring they are reliable, secure, and performant.
Design and build multi-agent workflows: Build stateful agentic applications using agent orchestration frameworks capable of coordinating multiple autonomous components.
State, memory, and long-running execution: Engineer control flows for non-deterministic systems, including message passing, persistent memory, recoverability, and interruptible execution for long-running tasks.
Standardised tool interfaces: Establish universal interfaces between agents, enterprise data sources, and operational tools to ensure modularity, reusability, and consistent governance.
Model integration and runtime optimisation: Build routing and fallback strategies across multiple model endpoints; optimise context management, latency, and inference cost while maintaining reliability.
Production deployment: Package and deploy workloads via containerisation and cluster orchestration, using cloud-native services for scaling, isolation, and secure runtime operations.
Requirements:
Experience: 5+ years in software engineering, data engineering, and/or machine learning engineering, with demonstrated ownership of production systems. Using Python, React/Angular, TypeScript, FastAPI, LangGraph, AI SDK, AWS, and Langfuse.
Full-stack development: Advanced proficiency in Python and React/Angular for building modular, testable, maintainable production services.
Generative AI in production: Proven experience building and deploying LLM-based applications and/or agentic systems in real-world environments.
Storage and retrieval expertise: Proven experience designing AI-ready storage layers across vector databases, relational and NoSQL databases, and modern lakehouse/warehouse architectures.
Cloud and infrastructure depth: Strong capability in deploying and scaling services on major cloud platforms using containerisation, cluster orchestration, CI/CD, and secure runtime practices.
LLM systems understanding: Strong grasp of retrieval-augmented generation, embeddings, context strategies, prompt/system design, and failure modes in deployed systems.
Hybrid engineering skillset: Ability to blend ML intuition (model behaviour, uncertainty, evaluation) with software excellence (APIs, async systems, reliability engineering).
Education: Bachelor's degree in computer science, engineering, mathematics, or a related technical field (or equivalent experience).
Technology Stack:
Backend: Python, FastAPI.
Frontend: React or Angular and TypeScript.
AI/LLM: AWS Bedrock, LangGraph, RAG pipelines, embeddings.
Observability: Langfuse or similar LLM observability tools.
Infra: Docker, Kubernetes/ECS, CI/CD.
Data: Vector DBs (Pinecone, OpenSearch, Weaviate, etc. ) and SQL/NoSQL.

Experience
5-9 yrs