Edge AI Engineer Intern: Inference & Orchestration

Iaas Lc; San Francisco (CA); On-site; USD 62,000 - 70,000; Part time

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Disability insurance

Paid time off

Job summary

Iaas Lc is offering an internship focused on AI model hosting, optimization, and orchestration. You will help profile and accelerate model inference on edge devices and contribute to scalable workflows with LangGraph and LangChain.

Ideal candidates are pursuing CS/engineering degrees or equivalent experience, with strong communication and a passion for ML systems, tooling, and optimization.

Qualifications

• Pursuing a degree in Computer Science, Engineering, or related field, or equivalent practical experience.
• Strong technical communication to articulate goals and decisions clearly.
• Familiarity with model inference, orchestration frameworks (LangGraph, LangChain), or AI systems work.
• Collaborative mindset with cross-functional teams and ownership of outcomes.

Responsibilities

• Work on model hosting and inference optimization, profiling, benchmarking, and accelerating model execution on resource-constrained devices.
• Contribute to orchestration frameworks and agent workflows; design robust, scalable orchestrations.
• Assist in model customization and fine-tuning of pre-trained language models for use cases.
• Collaborate with system software, design, and product teams to integrate work into the platform and communicate progress.
• Contribute to open-source projects or internal libraries related to inference or orchestration; take ownership of outcomes.

Skills

Python

PyTorch

TensorFlow

LangGraph

LangChain

Open-source contributions

Effective communication

Education

Pursuing CS/Engineering degree or equivalent

Tools

HuggingFace

FastAPI

LangGraph

LangChain

Profiling & optimization tools

Job description

Iaas Lc is offering an internship focused on AI model hosting, optimization, and orchestration. You will help profile and accelerate model inference on edge devices and contribute to scalable workflows with LangGraph and LangChain.

Ideal candidates are pursuing CS/engineering degrees or equivalent experience, with strong communication and a passion for ML systems, tooling, and optimization.