About the Company CodeNinja is a global AI and engineering services company helping enterprises build, scale, and operate intelligent systems. With 350+ engineers across four continents and 400+ successful deployments, CodeNinja enables organizations to harness artificial intelligence through Global Capability Centers, Work AI, Physical AI, and AI Labs. Recognized among Pakistan’s fastest-growing AI firms and a multi-award recipient on Clutch, CodeNinja empowers over 250 clients worldwide to innovate, automate, and compete in the intelligence economy. About the Role We are looking for a hands-on AI Engineer to design, develop, and operate AI-powered software systems that deliver immediate, real-world value. This role sits at the intersection of software engineering, product engineering, and applied AI, with a clear mandate: use AI to materially improve how software is built and what it can do. This is not a research or theoretical machine learning role. You will focus on practical implementation — building and integrating agentic systems, model-driven workflows, and AI-enabled capabilities directly into production applications, internal workflows, and customer-facing products. As CodeNinja advances its AI-first way of working, you will be a highly autonomous engineer, augmented by intelligent systems, treating models, agents, and context as first-class runtime components to improve leverage, quality, and speed in the systems you own. Key Responsibilities AI Engineering & Development • Design, build, and operate production-grade software systems that embed AI as a core capability rather than an add-on. • Build and integrate agentic systems that autonomously select tools, manage context, and execute multi-step tasks toward defined goals. • Implement Model Context Protocol (MCP) or equivalent mechanisms to manage context, tools, memory, and system boundaries in production. • Translate product requirements into AI-enabled implementations that are scalable, reliable, secure, and observable. • Apply AI through prompting, orchestration, model composition, evaluation, and deployment, focusing on runtime behavior rather than model training. • Treat model inputs, outputs, and behavior as versioned, testable components of the system. AI-First Software Development • Use AI directly in daily engineering work, including: • AI-assisted and AI-generated code • Autonomous and semi-autonomous engineering agents • AI-driven test generation, debugging, and refactoring • AI-enabled documentation and observability • Treat AI as a default everyday tool to increase personal and team leverage. • Iterate on prompts, policies, agent flows, and contextual inputs as part of normal development workflows. • Apply and refine AI-enabled development practices to reduce manual effort and improve delivery quality. Product & Platform Collaboration • Partner closely with Product, Scrum Masters, and engineers to deliver AI-powered features end to end — and take on these roles when needed, including working as a single-person team. This is true full-stack in an AI-powered environment. • Integrate AI systems with real-world services, APIs, and data sources in production applications. • Contribute to shared platforms, services, and internal tooling in line with established patterns and architectural direction. • Balance rapid iteration with sound engineering judgment and long-term maintainability. Quality, Reliability & Accountability • Own the quality of your deliverables across the full stack; partner with QA when available, but build AI agents that guarantee the quality of what you ship. • Ensure AI-enabled systems meet enterprise standards for security, performance, reliability, and compliance. • Implement safeguards, monitoring, and evaluation for AI behavior in production, including detection of hallucinations, regressions, and unintended behavior. • Treat evaluation, traceability, and explainability as ongoing engineering concerns. • Own solutions from initial design through deployment and ongoing operation. Continuous Improvement & Learning • Stay current on AI tools, platforms, models, and agentic patterns relevant to real-world software. • Experiment responsibly with new AI capabilities and turn learnings into concrete improvements. • Contribute to a culture of technical excellence, accountability, and continuous learning. Requirements Skills & Expertise Required • Bachelor's degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience. • Strong software engineering fundamentals, with experience building and operating production systems. • Hands-on experience building or working with real agentic AI systems, including giving models autonomy to select tools and execute multi-step tasks. • Experience using Model Context Protocol (MCP) or equivalent approaches to manage tools, context, and memory in production AI systems. • Solid technical understanding of AI models, including: • Model names and versions • Parameter sizes and context window limits • System prompts vs. user prompts • Trade-offs between models (latency, cost, reasoning quality) • Experience with open-source AI models and ecosystems, alongside commercial or hosted models. • Experience integrating AI systems with real-world services, APIs, and data sources. • Ability to evaluate AI systems beyond accuracy — including reliability, hallucination risk, traceability, and safety. • Experience addressing scaling concerns such as latency, cost optimization, caching, parallelization, and RAG vs. fine-tuning trade-offs. • Proven ability to take AI systems from prototype to pilot to production, with awareness of common failure modes and how to mitigate them. • Comfortable working autonomously in small, highly empowered teams. Preferred Skills • Experience integrating frontier and open-source models into SaaS or enterprise applications. • Familiarity with cloud-native architectures and modern development stacks. • Experience