Description

Build and own large-scale agentic systems and LLM infrastructure.

This role is on-site.

Responsibilities

• Design and implement complex, cross-cutting agentic systems spanning multiple products.
• Develop backend services, APIs, and data pipelines using Node.js, TypeScript, and Python.
• Integrate commercial and open-source LLMs into agentic workflows using LangGraph, LangChain, or similar frameworks.
• Manage distributed systems, queues, and streaming architectures with Kafka and Kubernetes.
• Drive technical direction and align teams on autonomous system reliability and deployment.

Required Skills

• 10+ years of experience building large-scale distributed systems.
• Strong proficiency in Node.js, JavaScript, and TypeScript.
• Deep experience with agentic AI stacks including planning, tool use, memory, and evaluation.
• Hands-on experience with Kafka, REST, gRPC, and event-driven architectures.
• Proficiency in cloud infrastructure (AWS or GCP) and container orchestration (Kubernetes).
• Experience with PyTorch, Hugging Face ecosystem, and model inference tooling.
• Strong engineering fundamentals in backend systems and data pipelines.

Preferred Skills

• Experience in fintech or regulated industries.
• Contributions to open-source AI or agentic frameworks.
• Familiarity with fine-tuning and model optimization.

Key Skills

Education

Bachelor's degree