AI Engineer — LLMs & Agentic Systems

Job Overview We are looking for an AI Engineer to design, develop, and improve AI-powered applications, LLM-based systems, and agentic workflows. The ideal candidate can move beyond basic prompt engineering to build reliable AI solutions that interact with APIs, use tools, process structured information, and automate complex engineering tasks. You will contribute to AI systems that support software testing, test-case generation, intelligent automation, and end-to-end quality engineering. Responsibilities Design and develop LLM-powered applications and AI agents. Build agentic workflows that interact with APIs, databases, and external tools. Develop retrieval-augmented generation (RAG) pipelines and knowledge-based AI systems. Integrate AI models from providers such as OpenAI, Anthropic, and other LLM platforms. Implement tool calling, structured outputs, context management, and multi-step reasoning workflows. Develop evaluation frameworks to measure AI accuracy, reliability, and consistency. Apply AI to software testing, including test-case generation, test execution assistance, and result analysis. Optimize prompts, model selection, latency, and inference costs. Implement safeguards, validation, observability, and error recovery for AI workflows. Collaborate with software and integration engineers to deploy production-ready AI systems. Requirements Strong programming skills in Python. Practical experience building applications using LLM APIs. Understanding of agentic AI architectures, tool calling, and workflow orchestration. Experience with prompt engineering, structured outputs, and AI response validation. Knowledge of REST APIs, JSON, databases, and software engineering best practices. Familiarity with Git, Docker, and deploying backend applications. Strong analytical and problem-solving skills. Ability to build, test, debug, and maintain production-oriented AI applications. Nice to Have Experience with MCP (Model Context Protocol). Experience with frameworks such as LangGraph, LangChain, or equivalent agent orchestration tools. Knowledge of RAG, embeddings, vector databases, and document processing. Experience evaluating LLM outputs, hallucination mitigation, and AI reliability. Experience with AI-assisted QA, browser automation, API testing, or cybersecurity applications. Familiarity with open-source models and self-hosted AI infrastructure. What We Offer The opportunity to build practical agentic AI products from the ground up. Hands-on work with AI agents and real-world automation systems. Technical ownership and opportunities to influence architecture. A collaborative environment focused on experimentation, engineering quality, and continuous learning.