Latest AI JobsBrowse Jobs
L

Forward Deployed Engineer – AI Inference (Intern)

lyceumBerlinProduct
Apply on company site
Salary
Not listed
Job type
Full-time
Experience
Intern
Posted
8 Oct 2026
Status
Open · checked 7d ago

About this role

Based in Berlin, the Forward Deployed Engineer – AI Inference (Intern) at lyceum is a full-time internship that manages technical AI inference deals and suits a student interested in customer-facing engineering. This position bridges the gap between technology and business by partnering directly with clients.

Role Overview

The Forward Deployed Engineer Intern takes charge of the technical aspects related to AI inference agreements. The position involves collaborating directly with clients to identify suitable configurations, models, and GPUs, while also coordinating closely with the commercial department to secure agreements. The role balances customer engagement with internal product development.

Key Responsibilities

Match client specifications with appropriate models, hardware configurations, and GPUs for dedicated inference.
Conduct technical meetings with clients to guide their decision-making process.
Partner alongside the commercial division to advance deals.
Assist with API and serverless customizations, transforming repetitive tasks into product features.
Convert client needs into precise technical specifications for the engineering group.
Gather performance benchmarks and insights to automate matching and customization workflows.

Requirements

Current enrollment in a degree program focused on computer science, data science, or a related discipline.
Familiarity with or interest in AI inference topics such as graphics processing units, large language models, and inference engines.
Genuine enthusiasm for client interaction and commercial operations alongside technical duties.
Effective communication abilities for interacting with both clients and engineers.
Entrepreneurial approach focused on achieving outcomes independently.
Ability to remain composed and constructive during critical discussions.
Fluency in the English language.

Nice to Have

Academic coursework or practical projects involving machine learning systems or inference engines like vLLM, TensorRT-LLM, or SGLang.
Background in model serving, performance tuning, benchmarking, or hardware sizing.
Prior internship experience at an inference or AI infrastructure enterprise.
Background working within startup environments.
Proficiency in the German language.

Skills and Tools

Large Language Models (LLMs)
Inference Engines
GPUs
vLLM
SGLang
TensorRT-LLM
APIs

About the Company

Lyceum operates as an early-stage enterprise focused on establishing sovereign and GDPR-compliant AI infrastructure designed for European deep-tech organizations. The company features a team with backgrounds originating from top universities, major technology firms, hedge funds, and artificial intelligence startups.

How to Apply

Interested candidates should submit their application through the official company careers page.

Skills and tech stack

vLLMSGLangTensorRT-LLMLLMLLMs

Questions candidates ask

Where is the Forward Deployed Engineer Intern role located?

The position is located in Berlin.

What background is required for applicants?

Applicants must be studying computer science, data science, or a closely related field, and have fluent English skills.

Is this a pure engineering position?

No, this is a hybrid role where a significant amount of time is spent interacting with clients and working alongside the commercial team.

What bonus qualifications are helpful for this internship?

Helpful bonus qualifications include coursework or projects on inference engines like vLLM, SGLang, or TensorRT-LLM, experience with GPU sizing or benchmarking, prior startup or AI infrastructure internships, and German language skills.

Ready to apply?

The application is on the official lyceum careers page.

Apply on company site