We are seeking an
AI Engineer with a strong, practical builder mindset to drive the development of next-generation, production-grade Generative AI applications.
In this role, you will move past basic wrappers and prompt engineering to architect complex, multi-stage agentic workflows, multi-agent systems, and optimized Retrieval-Augmented Generation (RAG) pipelines. You will bridge the gap between bleeding-edge AI models and highly scalable backend infrastructure.
Key Responsibilities- Design, build, and deploy multi-stage autonomous agent workflows, multi-agent systems, and advanced conversational workflows to support real-time interactions.
- Architect scalable backend services and robust APIs to support real-time AI inference and production-ready Agentic AI solutions.
- Build and optimize multi-stage RAG systems utilizing advanced data pipelines, vector search databases, and modern data platforms.
- Design and implement comprehensive logging, tracing, and automated evaluation frameworks to measure the reliability, accuracy, and relevance of LLM/GenAI outputs.
- Evaluate, fine-tune, and deploy custom foundation models across languages and modalities using proprietary and external datasets.
- Apply cutting-edge AI guardrails, responsible AI principles, and adversarial red-teaming strategies to ensure compliance, privacy, and security.
Requirements & Technical Skills:
- 3-5 years of hands-on experience in Machine Learning Engineering, Software Engineering, and production-level Generative AI/LLM technologies.
- Deep experience with LLM orchestration and multi-agent frameworks (e.g., LangGraph, LangChain, LlamaIndex, or CrewAI).
- Advanced mastery of Python and standard backend frameworks (e.g., FastAPI, Flask) with a strong builder profile over pure academic research.
- Proven experience deploying foundation models on enterprise cloud AI platforms (e.g., AWS Bedrock, Azure OpenAI, or GCP Vertex AI).
- Familiarity with LLM tracing and testing ecosystems (e.g., MLflow, LangSmith, Langfuse, Arize Phoenix, Ragas, TruLens).
- Solid understanding of Transformer architectures, NLP techniques, multimodal AI, token optimization, and semantic vector search.
