ML Engineer

This role is for one of the Weekday's clients

Requirements

Key Responsibilities

• Design, develop, and maintain agentic AI workflows using modern orchestration frameworks such as LangChain and LangGraph
• Build and optimize end-to-end RAG pipelines, including document ingestion, chunking strategies, embeddings, vector storage, retrieval, and evaluation
• Develop LLM-powered systems for automation, decision support, and knowledge-intensive use cases
• Create and manage prompt templates, agent behaviors, and multi-agent interaction flows
• Fine-tune, evaluate, and optimize LLMs, embedding models, and reranking strategies to improve accuracy, relevance, and performance
• Ensure AI systems meet production standards for performance, latency, observability, security, and safety
• Collaborate cross-functionally to translate business and product requirements into scalable AI architectures
• Continuously research emerging GenAI and LLM advancements and integrate relevant innovations into existing systems
  

What Makes You a Great Fit

• Strong hands-on experience with agentic AI frameworks, including building stateful workflows and multi-agent systems
• Deep understanding of RAG architectures, vector databases, and information retrieval techniques
• Proven ability to design and deploy production-grade LLM solutions using Python and cloud-based infrastructure
• Solid grasp of modern LLM ecosystems and experience integrating APIs from leading model providers
• Strong system design mindset with the ability to debug, optimize, and scale complex AI systems
• Experience with containerization, microservices, and DevOps practices for reliable deployment
• Curiosity and passion for staying current with advancements in GenAI, LLMOps, and prompt engineering
• Ability to clearly communicate technical concepts and collaborate effectively with diverse stakeholders