Backend Engineer: AI / Agent Systems (ES)

About the Client

Our client is an AI-native product company built to replace how billions of people manage their digital lives — starting with email, notes, and task tools that were never designed to be AI-native. It's backed by multi-million-dollar investment and built remote-first from day one, with a clear target: cut the time it takes users to get everyday things done by roughly 90%. That means solving the problems most AI products avoid — long-running workflows, persistent context, and reliable behavior under real-world, non-deterministic conditions. The team is small and high-talent-density by design, not by necessity, and moves at a pace that matches the scale of what it's building.
About the Role

As a Backend Engineer, AI, you'll own the inference and orchestration layer that powers every AI interaction in the product. Your work sits between models and users, where latency, correctness, reliability, and cost directly shape real-world experience. You'll build and operate production systems that turn model capability into fast, stable, observable APIs used across mobile and desktop clients.
What You'll Work On

-
Build and operate backend systems that serve AI-powered features in production

-
Design inference pipelines, orchestration layers, and service boundaries around models

-
Own production concerns: monitoring, logging, alerting, incident response

-
Optimize latency and throughput across inference, caching, batching, and streaming

Requirements

-
Strong backend engineering fundamentals in production environments

-
Experience running high-throughput, low-latency services

-
Familiarity with AI inference patterns (LLMs, embeddings, multimodal)

-
Comfortable debugging distributed systems under load

-
A bias toward shipping and learning from production behavior

Tech Stack

Python · Node.js · PyTorch · OpenAI / Anthropic / open-source LLMs · SQL & NoSQL · Kubernetes · Docker
What Success Looks Like

-
Backend systems run reliably at scale, handling production AI traffic with low latency and high throughput

-
APIs are stable, clear, and support seamless integration with frontend and ML systems

-
Production incidents are detected, diagnosed, and resolved quickly, minimizing user impact

-
Iterative improvements based on real usage continuously raise system performance and reliability

What to Expect

The best products in the world are built by small, world-class, hands-on teams. Decisions are made collectively, at rapid speed — balancing high-quality shipping with fast learning. You'll be expected to bring structure, exercise judgment, and execute independently.

Compensation and benefits are competitive and vary by location; the package includes base salary and equity, discussed openly with you as part of the process.

If there's a fit, expect 3–4 interviews total, followed by a prompt, transparent decision.

Originally posted on Himalayas