About the job
At FourKites, we are committed to addressing intricate challenges that have significant real-world implications. From managing medical supplies for Cardinal Health to ensuring the timely delivery of groceries for Walmart, our platform empowers customers to maintain global supply chains that are not only efficient but also agile and sustainable.
We invite you to join a dynamic team of innovative problem solvers who celebrate diversity, lead with empathy, and prioritize inclusivity.
We are on the lookout for a seasoned Senior AI Engineer to become a vital member of our Shipment Visibility team. In this role, you will be instrumental in developing and expanding our next-generation Intelligent Tracking platform. Your work will involve pioneering agent-based systems that are revolutionizing supply chain operations for Fortune 500 companies, delivering substantial business value through intelligent automation.
Your Key Responsibilities:
Technical Leadership:
- Design and implement large-scale AI agent systems and orchestration frameworks (LangGraph, LangChain, and similar architectures).
- Lead the architecture design for multi-agent systems managing complex business workflows.
- Optimize deployment strategies utilizing both LLMs and SLMs tailored to specific use case requirements.
- Create natural language-configurable frameworks for business process automation.
- Implement multi-modal AI systems for comprehensive document understanding (tables, charts, layouts).
AI/ML Implementation & Optimization:
- Deploy and optimize LLMs/SLMs in production environments using advanced fine-tuning techniques (LoRA, QLoRA, DPO).
- Implement quantization strategies (INT8, INT4) and model distillation for edge deployment.
- Build evaluation frameworks including LLM-as-judge systems and conduct regression testing.
- Design streaming architectures for delivering real-time LLM responses (SSE, WebSockets).
- Create semantic caching and embedding-based retrieval systems.
- Develop strategies for GraphRAG and long-context handling (100k+ tokens).
System Architecture & Engineering:
- Design scalable microservices with extensive observability (LangSmith, Arize, custom telemetry).
- Build secure multi-tenant systems with preventive measures against prompt injection and output validation.
- Implement cost optimization via intelligent model routing and fallback strategies.
- Develop document processing pipelines integrating OCR and layout understanding.
- Create event-driven architectures for real-time shipment tracking and exception handling.
Data & Infrastructure:
- Construct data pipelines for training data curation and model performance enhancement.

