Senior Inference Engineer

Loft Labs, Inc. dba vCluster Labs; United States; On-site; USD 140,000 - 190,000; Full time

Job summary

Loft Labs, Inc. dba vCluster Labs is seeking a Senior Inference Engineer to build and optimize the platform's inference layer. The role involves deploying models to production and managing the entire query-to-response pipeline in a remote environment.

The candidate will deploy models, operate serving infra with vLLM/SGLang/TensorRT-LLM, and influence the engineering direction in collaboration with Product for future developments.

Qualifications

• Experience deploying and serving LLMs using frameworks such as vLLM, SGLang, or TensorRT-LLM.
• Hands-on knowledge of inference optimization techniques like quantization, batching, caching, and routing.
• Strong programming skills in Python or Golang with real production code experience.
• Ability to communicate technical concepts clearly to both technical and non-technical stakeholders.
• Familiarity with containerized environments (Docker, Kubernetes) is a plus.

Responsibilities

• Deploying models to production and owning the full pipeline from query to response.
• Building and operating serving infrastructure using frameworks like vLLM, SGLang, or TensorRT-LLM.
• Leading the engineering direction for inference, collaborating with Product to shape future developments.

Skills

LLM deployment

Inference optimization

Python

Golang

Communication

Tools

Docker

Kubernetes

Job description

Partnering directly with the CTO, the full-time Senior Inference Engineer will build and optimize the platform's inference layer, deploying models to production and managing the entire query-to-response pipeline in a remote environment.

Key responsibilities

• Deploying models to production and owning the full pipeline from query to response
• Building and operating serving infrastructure using frameworks like vLLM, SGLang, or TensorRT-LLM
• Leading the engineering direction for inference, collaborating with Product to shape future developments

Required qualifications

• Experience deploying and serving LLMs using frameworks such as vLLM, SGLang, or TensorRT-LLM
• Hands‑on knowledge of inference optimization techniques like quantization, batching, caching, and routing
• Strong programming skills in Python or Golang with real production code experience
• Ability to communicate technical concepts clearly to both technical and non-technical stakeholders
• Familiarity with containerized environments (Docker, Kubernetes) is a plus