Backend Engineer (LLM inference) (Fully Remote)

Aleroy; United States; Remote; USD 140,000 - 180,000; Full time

Benefits offered by this job

24 days annual leave

Health insurance

Performance-based incentives

Job summary

Aleroy in the United States is seeking a senior backend engineer to own the architecture and evolution of our core services powering AI inference. You will translate ambiguous problems into clear technical plans and drive decisions end to end.

Design OpenAI-compatible APIs for chat completions, streaming, and tool calls, optimize PostgreSQL data models, and implement caching with Redis and Valkey. Join a small, senior team that values ownership, fast execution, and low bureaucracy.

Qualifications

• Experience owning backend architecture and delivering end-to-end technical decisions.
• Strong API design skills for scalable services and AI tooling.
• Experience with PostgreSQL and caching strategies (Redis).

Responsibilities

• Own the architecture and evolution of core backend services with real technical ownership.
• Design OpenAI-compatible APIs for chat completions, streaming, and tool calls.
• Optimize data models in PostgreSQL and use Redis/Valkey for caching.

Skills

Backend architecture

API design

OpenAI API familiarity

PostgreSQL

Redis caching

Tools

PostgreSQL

Redis

Valkey

Job description

• Own the architecture and evolution of core backend services with real technical ownership.
• Turn ambiguous problems into clear technical plans and drive decisions end to end.

What You Will Own:

• Design OpenAI-compatible APIs for chat completions, streaming, and tool calls.
• Optimize data models in PostgreSQL and use Redis/Valkey for caching.

What We Offer:

• Real ownership of the backend powering Aleroy's inference platform.
• 24 days annual leave, health insurance, and performance-based incentives.
• A small, senior team with fast execution and low bureaucracy.

Aleroy

Aleroy is building a unified platform for high-performance AI inference, helping companies deploy and run AI models at scale through a single API. They operate in small, senior teams with low bureaucracy, focusing on reliable, scalable AI infrastructure.