Engineering Manager, AI Serving & APIs

Jobgether SRL; United States; Remote; USD 225,000 - 350,000; Full time

Benefits offered by this job

Remote-first environment

Fully paid medical, dental and vision

401(k) matching

Generous PTO

Company-provided computer

Job summary

Jobgether SRL is seeking an Engineering Manager to lead the API serving and AI inference team in a remote-first, United States–based role. You will drive technical leadership across tokenization, structured generation, reasoning, and model integration, while shaping the roadmap and ensuring API fidelity, latency, and reliability.

You will collaborate with compiler, accelerator, and production platform teams to scale serving capabilities and ownership.

Qualifications

• Experience leading ML infra teams or LLM serving.
• Strong C++ systems background and Python proficiency.
• Ability to translate requirements into roadmaps with ownership.
• Experience recruiting and developing engineers across levels.
• Deep understanding of LLM serving concepts and APIs.
• Experience with AI accelerators is valuable.

Responsibilities

• Lead and grow the API serving and model integration teams.
• Define technical and organizational roadmaps covering API compatibility and model support.
• Own API fidelity including endpoints, streaming, and error handling.
• Collaborate with compiler, accelerator, and platform teams.
• Establish ownership boundaries and release gates for new models.
• Translate customer priorities into sequenced engineering initiatives.
• Ensure serving latency and reliability targets are met.

Skills

LLM inference

C++

Python

Roadmap planning

Team leadership

APIs

Communication

Hardware collaboration

Tools

vLLM

TensorRT-LLM

SGLang

XGrammar

Hugging Face tokenizers

Job description

Jobgether SRL is seeking an Engineering Manager to lead the API serving and AI inference team in a remote-first, United States–based role. You will drive technical leadership across tokenization, structured generation, reasoning, and model integration, while shaping the roadmap and ensuring API fidelity, latency, and reliability.

You will collaborate with compiler, accelerator, and production platform teams to scale serving capabilities and ownership.