Senior AI Engineer

KlearNow.ai•California, CA

2d•Hybrid

About The Position

KlearNow is building the intelligence layer for global trade and logistics. We turn fragmented, messy data into instant, reliable intelligence, enabling AI to reason and act in high-stakes, real-world environments. We are a small, sharp team operating at the frontier, and we are looking for builders who want to define the technical foundation from the ground up. As a Senior AI Engineer on our Applied AI team, you will design and deploy production-grade agentic AI systems that transform real-world workflows at scale. This role is ideal for someone who thrives on ownership, is energized by ambiguity, and wants to ship consequential systems, not just run experiments. You will own end-to-end AI pipelines from data ingestion through retrieval, orchestration, and output, while also shaping product direction and engineering culture.

Requirements

4+ years of hands-on software engineering experience; startup experience strongly preferred
Proven track record shipping production-grade AI systems, not just prototypes
Strong hands-on experience with: Agent architectures, LLM systems, and RAG pipelines
Strong hands-on experience with: Retrieval, grounding, and orchestration techniques
Strong hands-on experience with: Python (strong proficiency) and TypeScript (working knowledge)
4+ years of infrastructure experience (cloud services, distributed systems)
4+ years working with containerization tools such as Docker and Kubernetes
2+ years of experience building with Large Language Models (LLMs) in production
Full-stack ownership mindset — comfortable operating across the entire system
Strong data instincts and experience working with messy, real-world datasets
Must be authorized to work in the United States (no visa sponsorship available)
Ability to commute to the San Jose, CA office (Hybrid Schedule)

Nice To Haves

Experience with evals frameworks and AI quality measurement
Background in AI infrastructure or distributed systems
Exposure to automotive, logistics, or other physical-world domains
MLOps / DevOps experience; CI/CD pipelines, Docker, Kubernetes
Former founder or early employee at a startup

Responsibilities

Design and build multi-agent systems that reason across messy, real-world data
Own end-to-end AI pipelines — data → retrieval → orchestration → output
Develop evaluation frameworks, benchmarks, and quality loops to ensure reliability
Build and scale data ingestion and retrieval infrastructure
Integrate LLMs with enterprise data, tools, and workflows using frameworks such as: Agno, LangChain, LlamaIndex, and Semantic Kernel
Integrate LLMs with enterprise agent deployment using tools like Claude Code, Cursor, and AugmentCode
Ship full-stack product features in close collaboration with end users
Help define technical architecture, product direction, and engineering culture
Write clear, well-structured Python and TypeScript code for production ML systems