Backend Engineer

Axe Recruiting; United States; À distance; USD 140 000 - 180 000; Plein temps

Résumé du poste

Axe Recruiting is seeking an experienced backend engineer to own the inference and orchestration layer that sits between the models and every user interaction. You will build and run production systems that turn model capability into fast, observable APIs for mobile and desktop clients.

You’ll design inference pipelines, orchestration layers and service boundaries around models, and own production concerns such as monitoring, logging and incident response.

Qualifications

• Experience running high-throughput, low-latency services.
• Familiarity with AI inference patterns (LLMs, embeddings, multimodal).
• Comfort debugging distributed systems under load.
• Bias toward shipping and learning from production behavior.

Responsabilités

• Build and operate the backend systems that serve AI-powered features in production.
• Design the inference pipelines, orchestration layers and service boundaries around models.
• Own production concerns: monitoring, logging, alerting and incident response.
• Optimize latency and throughput across inference, caching, batching and streaming.
• Deliver stable, clear APIs that integrate cleanly with frontend and ML systems.
• Detect, diagnose and resolve production incidents quickly, keeping user impact low.
• Drive continuous gains in performance and reliability from real usage.

Connaissances

Backend engineering

Low latency

Distributed systems

Production monitoring

AI inference patterns

Outils

Python

Node.js

PyTorch

SQL

NoSQL

Kubernetes

Docker

Description du poste

Own the inference and orchestration layer that sits between the models and every user interaction.

The Opportunity

Every AI interaction in our client’s product runs through the layer this engineer owns. The client is a well-funded AI applications company, backed by an established technology company in Southeast Asia and building for a global market, and it is rebuilding everyday productivity apps as AI-native products. The backend seat, focused on AI and agent systems, sits between models and users, where latency, correctness, reliability and cost show up directly in the experience. You will build and run the production systems that turn model capability into fast, stable, observable APIs for the mobile and desktop clients.

Role Snapshot

• Location: United States, United Kingdom, Europe (Ireland, Germany, Poland, Portugal, Sweden, Switzerland) or Asia (Singapore, South Korea, China)
• Work Model: Remote in most locations; hybrid in the UK and Seoul
• Employment Type: Full-time
• Compensation: Competitive, shared on intro call
• Team: Engineering, backend and AI systems

What You’ll Own

• Build and operate the backend systems that serve AI-powered features in production.
• Design the inference pipelines, orchestration layers and service boundaries around models.
• Own production concerns: monitoring, logging, alerting and incident response.
• Optimize latency and throughput across inference, caching, batching and streaming.
• Deliver stable, clear APIs that integrate cleanly with frontend and ML systems.
• Detect, diagnose and resolve production incidents quickly, keeping user impact low.
• Drive continuous gains in performance and reliability from real usage.

What You Bring

• Strong backend engineering fundamentals in production environments.
• Experience running high-throughput, low-latency services.
• Familiarity with AI inference patterns (LLMs, embeddings, multimodal).
• Comfort debugging distributed systems under load.
• A bias toward shipping and learning from production behavior.

Why This Role

• A central seat: every AI interaction in the product depends on this layer, so the work is visible and consequential.
• A practical stack: Python, Node.js, PyTorch, commercial and open-source LLMs, SQL and NoSQL, Kubernetes and Docker.
• A small, hands-on team with a high bar, where engineers exercise their own judgment and execute independently.
• A short hiring process: three to four interviews, assessed by engineers, with a prompt decision.

Not the Right Fit If

• You want to build services at arm’s length from production. Monitoring, alerting and incident response are part of this job.
• You have no interest in how models behave. Inference patterns, streaming and batching are core to the role.
• You need detailed specifications before you start; this team moves quickly and learns from what happens in production.