LLM Backend Engineer - Multimodal Infra & Scale

ByteDance; San Jose (CA); On-site; USD 128,000 - 256,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

401(k) with company match

Parental leave

Short/long-term disability

Life insurance

Wellbeing benefits

Paid holidays

Paid sick days

Paid Personal Time

Job summary

ByteDance’s Volcano Ark MaaS team is hiring a software engineer to design and develop core components for a scalable, multimodal large model service platform. The role focuses on API capabilities for text dialogue and multimodal generation within a cloud-native framework.

Candidates should have CS degrees and practical backend development experience, with knowledge of Kubernetes, Docker, Istio, and Envoy. Salary ranges reflect the competitive market in San Jose and the broader U.S.

Qualifications

• Bachelor’s or Master’s degree in Computer Science or a related discipline.
• Proficient in Golang, Java, C++, or Python with solid CS fundamentals.
• Understanding of backend systems, databases, networks, OS, and distributed systems.

Responsibilities

• Design and develop core components of the Volcano Ark MaaS platform, supporting API capabilities for text dialogue, multimodal understanding, and multimodal generation.
• Participate in cloud-native architecture evolution, including Service Mesh, load balancing, and intelligent routing; design and implement high-availability solutions.
• Perform system-level performance tuning for long connections, high throughput, streaming output, and low latency in multimodal large model inference scenarios.
• Ensure system stability for large-scale model invocation scenarios and resolve architectural bottlenecks caused by sudden traffic spikes.

Skills

Golang

Java

C++

Python

Education

Bachelor's or Master's in Computer Science or related discipline

Tools

Kubernetes

Docker

Istio

Envoy

Job description

ByteDance’s Volcano Ark MaaS team is hiring a software engineer to design and develop core components for a scalable, multimodal large model service platform. The role focuses on API capabilities for text dialogue and multimodal generation within a cloud-native framework.

Candidates should have CS degrees and practical backend development experience, with knowledge of Kubernetes, Docker, Istio, and Envoy. Salary ranges reflect the competitive market in San Jose and the broader U.S.