Full Stack Developer PK (Female only office)

PLEASE DO NOT SEND ANY DIRECT EMAILS TO ANY TEAM MEMBERSPLEASE DO NOT SEND ANY DIRECT EMAILS TO ANY TEAM MEMBERSPLEASE DO NOT SEND ANY DIRECT EMAILS TO ANY TEAM MEMBERSPLEASE READ THE COMPANY DESCRIPTION AND SEE IF YOU FITWE ARE A FEMALE-ONLY OFFICECompany DescriptionContextual Staffing connects innovative companies with exceptional tech talent, focusing on regions with workplace vulnerabilities, particularly for talented women. Contextual Staffing creates life-changing careers by building teams with a purpose and supplies businesses with highly motivated, dedicated, and loyal professionals. The company's simple, all-inclusive subscription model facilitates international payroll, HR, and compliance, allowing businesses to scale with top-tier remote talent. Their areas of expertise include web development, UI/UX design, and mobile app development.Role DescriptionJoin us to create next-generation AI solutions driven by Generative AI technologies, serving a range of regulated industries. Our engineering stack spans a Next.js + React + Tailwind frontend and a Python backend (FastAPI/Django/Flask) with RAG pipelines, vector databases and multi-agent workflows. You will own the architecture, scalability, and reliability of the platform - taking it from demo to production without breaking.We’re looking for a senior engineer with solid softwareengineering fundamentals and at least one year of hands-on experience delivering generative AI applications in production.Key Responsibilities Architecture & Scaling: Decompose monoliths into microservices with clean APIs, deployed via Docker and Kubernetes with auto-scaling and resilience.Frontend Engineering: Build secure, high-performance chat UIs (Next.js App Router, React 19, Tailwind, Radix UI), including robust SSE streaming lifecycle management.Backend Engineering: Design scalable FastAPI services for authentication, RBAC, file ingestion, chat streaming, and orchestration.Generative AI & LLM Development: Architect and optimise RAG systems using vector DBs (Qdrant / Pinecone / Weaviate); design and deploy conversational AI experiences.Real-Time & Voice Readiness: Implement WebRTC-based real-time communication pipelines to enable future voice-AI applications.Async & Reliability: Implement task/message queues (Celery, RabbitMQ, Kafka, Redis Streams) for long-running workflows, retries, and event sourcing.Data & Memory Layers: Work with Postgres, MongoDB, Redis and vector DBs for retrieval.Security & Compliance: Enforce secure auth flows (OAuth2, JWT, 2FA), RBAC/ABAC, CSP/security headers, and PII masking.Observability & CI/CD: Own GitHub Actions pipelines, automated tests, structured logging, metrics, traces, and safe rollout strategies (blue-green, canary).Collaboration: Partner with product, AI, and infra teams to deliver reliable, production-grade AI systems.Must Have 8+ years of professional software engineering experience with production system ownershipStrong frontend skills: Next.js 13+/15, React, Tailwind, RadixMobile experience: production-grade mobile apps (React Native/Flutter, API integration, deployment) Strong backend skills: Python (FastAPI / Django / Flask) with async I/O Proven experience with Docker and scalable microservices on KubernetesKnowledge of WebRTC or similar real-time communication technologiesDeep understanding of async processing, queues, retries, and idempotencyData expertise: Postgres, MongoDB, Redis • Security-first mindset: OAuth2, JWT, RBAC/ABAC, 2FACI/CD discipline: GitHub Actions (or equivalent), automated testing, code-quality gatesObservability skills: logging, metrics, traces, debugging in productionGenerative AI Experience (>= 1 year) Building and deploying generative-AI applications in production Practical experience with RAG pipelines and vector database operationsLLM integration, prompt engineering, and model-optimisation techniquesAI-safety measures, evaluation frameworks, and responsible-AI practicesFamiliarity with conversational-AI / chatbot architecturesNice to Have AI-agent orchestration frameworks (LangGraph, AutoGen, Semantic Kernel)LLM fine-tuning (LoRA / QLoRA) and advanced prompt optimisation • Background in regulated industries (finance, healthcare, legal)Cloud operations (AWS / GCP / Azure) and Infrastructure as Code (Terraform)Experience with MLOps pipelines and model-deployment strategies