Full Stack Engineer

TECHNICAL REQUIREMENTS

Generative AI & Agentic Development ✦ Core Requirement

This is not a nice-to-have. We expect this engineer to code primarily through agentic AI tools, move faster because of them, and bring a structured, production-grade approach to AI-assisted development — not ad-hoc prompting.

• Fluent daily use of an AI-assisted coding environment — Claude Code is strongly preferred; Cursor or GitHub Copilot are equally considered.

• Proven ability to structure a robust, project-level agentic development environment, including:

• Project instruction files (e.g. CLAUDE.md) that encode architecture decisions, conventions, and constraints the agent must respect.

• Custom reusable skills and tools that extend agent capabilities for repeatable tasks.

• Rule sets and guardrails that enforce code quality, security standards, and team conventions automatically.

• Context and memory management — structuring prompts, sessions, and handoffs so agents remain accurate across long tasks.

• Multi-agent orchestration — decomposing complex engineering tasks across coordinated agent pipelines.

• Experience building production RAG pipelines, embedding workflows, or autonomous agentic systems.

• Hands-on LLM API integration — Anthropic, OpenAI, or equivalent — with strong prompt engineering discipline.

• Critical evaluation of AI-generated output for correctness, security, and long-term maintainability.

Backend & APIs

• Fluency in at least two of: Node.js, Python, Java — in production services.

• Deep GraphQL experience: schema-first design, resolver patterns, and federation.

• Strong grasp of event-driven and async architectures; OAuth 2.0 / JWT security standards.

Frontend

• Advanced React.js — performance optimisation, scalable state management, component architecture.

• Micro-frontend architecture experience with Module Federation or equivalent.

Data & Cloud

• MongoDB (aggregation, indexing), relational databases, and full-text / semantic search.

• Cloud-native engineering on AWS or equivalent: compute, messaging, storage, observability, and IAM.

• Serverless and event-driven patterns; security-first mindset across all infrastructure decisions.

Delivery & Practices

• CI/CD pipelines with any modern tooling; container-native Docker workflow.

• Automated testing at all levels and structured observability practices.

NICE TO HAVE

• Kubernetes, Helm, and Terraform experience.

• Vector databases or embedding-based search for semantic retrieval.

• GraphQL Federation across independently deployable services.

• Open-source contributions in AI, developer tooling, or cloud engineering.

Scope of work:

• Design and deliver scalable microservices and micro-frontend applications across the full stack.

• Integrate Generative AI capabilities — LLM APIs, RAG pipelines, and agentic workflows — into production systems.

• Own GraphQL API design, cloud infrastructure, and CI/CD pipelines end-to-end.

• Drive code quality through reviews, test automation, and observability standards.

• Evaluate and adopt emerging AI tooling; mentor engineers and contribute to technical roadmap.