Job Title : Generative AI Engineer (LLM, RAG, and AI Agents)
About the Role
We are seeking a highly skilled and innovative Generative AI Engineer to join our team and build the next generation of intelligent systems. This isn't about building simple chatbots. You will be at the forefront of AI development, creating sophisticated AI agents that can reason, plan, and interact with complex tools and data sources. If you are passionate about moving beyond basic LLM applications and building truly autonomous systems, this role is for you.
What You'll Do
- Design and Build AI Agents : Architect and implement multi-step AI agents that can perform complex tasks, use external tools via API calls, and make decisions autonomously.
- Implement Advanced RAG Pipelines : Develop and optimize Retrieval-Augmented Generation (RAG) systems from the ground up, ensuring our models have access to relevant, real-time information from diverse data sources.
- Develop LLM-Powered Workflows : Create robust, production-grade applications that leverage the capabilities of state-of-the-art Large Language Models (e.g., GPT-4, Claude 3, Llama 3).
- Evaluate and Optimize Performance : Design and implement rigorous evaluation frameworks to measure agent performance, accuracy, and efficiency, and continuously iterate to improve results.
- Integrate and Deploy : Work closely with MLOps and software engineers to deploy your AI agents as scalable and reliable services.
- Stay on the Cutting Edge : Research and experiment with the latest advancements in agentic AI, RAG techniques, and LLM architectures to ensure our solutions remain best-in-class.
Must-Have Qualifications
Professional Experience : 5+ years of hands-on experience in AI / ML engineering, with a specific focus on Natural Language Processing (NLP) or Generative AI.Hands-on LLM Experience : Proven experience building and deploying applications using major LLMs (e.g., via APIs from OpenAI, Anthropic, Google, or using open-source models).Expertise in RAG : Demonstrable, hands-on experience designing, building, and optimizing RAG pipelines, including familiarity with vector databases (e.g., Pinecone, Chroma, Weaviate) and embedding techniques.Agentic AI Implementation : Proven experience building AI agents that utilize frameworks like LangChain, LlamaIndex, or custom solutions to perform multi-step reasoning and tool use.Programming Excellence : Expert-level proficiency in Python and common AI / ML libraries (e.g., PyTorch, TensorFlow, Hugging Face).Preferred Qualifications
Experience with fine-tuning Large Language Models for domain-specific tasks.Familiarity with MLOps principles and tools (e.g., Docker, Kubernetes, MLflow) for deploying models in a production environment.Contributions to open-source AI projects or a strong portfolio of personal projects (e.g., GitHub).Published research in a relevant AI / NLP field.Experience building scalable, low-latency AI services.