Remote Senior Backend Engineer - AI, RAG & Vectors

web; United States; Remote; USD 120,000 - 210,000; Full time

Benefits offered by this job

Remote work

Health coverage

Retirement matching

Paid leave

Job summary

web is seeking a senior backend engineer to build and operate AI-powered product features at scale. You’ll own architecture through deployment, including asynchronous APIs, multi-agent workflows, and retrieval systems.

You will design REST/WebSocket APIs in Python, connect language model providers, and implement retrieval-augmented generation pipelines with vector databases. Remote work options are available.

Qualifications

• At least five years building production backend systems in Python with asynchronous I/O.
• Experience designing and scaling REST or asynchronous APIs and maintaining clean service architecture.
• Practical experience integrating language model APIs and building RAG systems with vector databases.
• Strong relational database skills, including schema design, query tuning, and migrations.
• Experience owning CI/CD workflows and applying AI tools across software delivery, including guardrails.

Responsibilities

• Design and scale asynchronous REST and WebSocket APIs in Python with clear service boundaries.
• Build multi-agent workflows and connect multiple language model providers via an integration layer.
• Develop retrieval-augmented generation pipelines backed by vector search and evolving schemas/migrations.
• Track service reliability, latency, and AI usage costs with structured logs and metrics.
• Own the delivery path from code checks to packaging and deployment, including safeguarding data-use.

Skills

Python

Async I/O

API design

CI/CD

LLM/AI tooling

Tools

Vector databases

Language model APIs

Job description

web is seeking a senior backend engineer to build and operate AI-powered product features at scale. You’ll own architecture through deployment, including asynchronous APIs, multi-agent workflows, and retrieval systems.

You will design REST/WebSocket APIs in Python, connect language model providers, and implement retrieval-augmented generation pipelines with vector databases. Remote work options are available.