Experience Range: 2 to 4 years of experience, including at least 2 years specifically focused on developing LLM-based applications, RAG systems, or AI agent workflows Key Responsibilities:
Design and build end-to-end AI agent workflows, from initial prompt design through production deployment, ensuring scalable and reliable solutionsDevelop and optimize Retrieval-Augmented Generation (RAG) pipelines by implementing chunking strategies, embedding models, retrieval ranking, and context window management for precise information retrievalBuild and iterate on prompt engineering layers, systematically testing and refining prompts and chain-of-thought strategies to deliver consistent outputs across diverse inputsImplement tool orchestration within agent workflows, integrating agents with databases, rule engines, validation systems, and formatting tools for seamless operationEstablish automated quality checks and validation layers to proactively identify and resolve issues before outputs reach human reviewersCollaborate with Data Scientists to instrument solutions for measurement, developing evaluation frameworks and tracking solution performance against defined targetsDeploy, monitor, and maintain AI/ML solutions in production environments, ensuring reliability, scalability, and robust error handlingDesign and implement feedback loops to capture expert review data and translate it into measurable improvements in agent performanceRequired Skills:
Advanced proficiency in PythonHands-on experience with LLM frameworks such as LangChain or LlamaIndexExpertise in prompt engineering for systematic testing and iterationDeep understanding of RAG architectures including embedding models, vector stores, retrieval strategies, and re-rankingExperience building multi-step agent workflows with tool use and branching logicExperience deploying and maintaining AI/ML solutions in production environmentsExperience with data pipeline development for feeding AI systemsPreferred Skills:
Experience with multi-agent orchestration frameworksBackground in content generation, translation, or document processing solutionsFamiliarity with feedback loops, RLHF, or reward model trainingKnowledge of multi-modal AI systems including voice-to-text, document understanding, and image analysisExperience with evaluation frameworks for generative AI and automated scoringExperience with LLM cost optimization strategies such as model routing, caching, and prompt compressionDesired Qualifications:
Bachelor's degree in Computer Science, Data Science, Information Technology, Statistics, or a closely related disciplineCertification in Machine Learning or Artificial Intelligence (e.g., TensorFlow Developer Certificate, AWS Certified Machine Learning – Specialty)Certification in LLM engineering or generative AI (e.g., DeepLearning.AI Generative AI with LLMs)