• Design and develop Agentic AI applications using LLM frameworks (LangChain, AutoGPT, CrewAI, Semantic Kernel, or similar) • Architect and implement multi-agent systems for enterprise-grade solutions • Integrate AI agents with APIs, databases, internal tools, and external SaaS products • Lead and mentor a cross-functional team across global time zones • Optimize performance, context retention, tool usage, and cost efficiency • Build reusable pipelines and modules to support GenAI use cases at scale • Ensure enterprise-grade security, privacy, and compliance standards in deployments • Collaborate directly with clients and senior stakeholders

• Architect and implement Generative AI features leveraging Large Language Models (LLMs), RAG frameworks, and agent orchestration. • Design scalable systems translating complex product requirements into modular, cloud-native software. • Contribute to the continuous evolution of our platform using Java, Kafka, and cloud-native best practices (AWS/Azure). • Mentor junior engineers, conduct deep-dive code reviews, advocate for high-quality, testable, and maintainable source code. • Collaborate in cross-functional agile squads to launch production-ready applications solving real-world transportation challenges.

• Architect and implement the generative intelligence core of our upcoming project • Design the RAG (Retrieval-Augmented Generation) architectures • Select the appropriate model stacks • Ensure AI outputs are grounded, safe, and performant • Work in lockstep with the Technical Leader to integrate AI services • Mentor the team on AI engineering best practices

This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more. Role Description We are building the most advanced AI Agent for the Web3 industry, leveraging the largest proprietary dataset in the field. We seek a core algorithm engineer to architect AI Agent systems, optimize end-to-end RAG pipelines, implement LLM training/alignment, and deploy scalable. Core Responsibilities - Develop AI Agent Systems: Build intelligent search and task execution agents using ReAct, planning, and multi-agent frameworks (e.g., LangGraph, Dify, CrewAI) - Optimize End-to-End RAG Pipelines: Build and refine efficient RAG systems from ingestion, chunking, and embedding to hybrid vector search (OpenSearch), implementing precise grounding and citation - LLM Training & Alignment: Conduct advanced post-training (SFT, RLHF, continual pretraining) and align models for reliable JSON-schema function calling and external tool usage - Automated Evaluation & Iteration: Build offline/online evaluation pipelines using synthetic QA, retrieval metrics, and hallucination detection to continuously improve system performance and stability Qualifications - Bachelor's or Master's degree in Computer Science, AI, Machine Learning, or a related field - 3+ years of experience developing AI systems, with a focus on RAG, Agent architectures, or LLM training/optimization - Proficiency in Python and key ML frameworks (PyTorch/TensorFlow), with experience in distributed training and high-performance inference - Hands-on, in-depth experience in at least two of the following domains: - End-to-end RAG pipeline development and optimization with OpenSearch/vector databases - AI Agent framework development (LangGraph, CrewAI, ReAct) - Advanced LLM training (SFT, RLHF, LoRA) and alignment techniques - Excellent problem-solving and systems thinking skills. Passion for Web3 and AI is a plus Key Outcomes - Deliver a high-accuracy, low-latency AI Agent system to power intelligent Web3 applications - Achieve continuous improvement in RAG retrieval accuracy and establish an automated evaluation and iteration loop - Drive LLM performance optimization