Senior Backend Engineer: AI Production & Observability

7Seventy; United States; Hybrid; USD 175,000 - 220,000; Full time

Benefits offered by this job

100% employer-paid medical, dental, &视

Vision insurance for employees

Dependent coverage 50%

Home office stipend

Job summary

7Seventy is seeking a Senior Backend Engineer to own AI-powered backend systems—from rapid prototyping to production deployment and ongoing evaluation.

You will build APIs, LLM agents, and RAG pipelines, while shaping architecture, reliability, and best practices across data pipelines, observability, and AI services.

The role emphasizes ownership, rapid iteration, and collaboration with Product, Design, and GTM teams to define scope and success metrics.

Qualifications

• 7+ years building production backend systems in Python or equivalent.
• Experience shipping prototypes to production with testing and observability.
• Hands-on with LLM features, tool/call use, and evaluation frameworks.
• Strong SQL, data pipelines, and scalable backend design.

Responsibilities

• Ship AI to production with scalable, observable services.
• Develop APIs, LLM agents, and RAG pipelines powering AI apps.
• Build reliable backend systems with SLAs, rollbacks, and cost controls.
• Create evaluation and observability frameworks for AI services.
• Collaborate with Product, Design, and GTM teams on scope and metrics.
• Improve reliability via monitoring, alerts, and incident response.

Skills

Backend engineering

Ownership

Observability

Experimentation

Python

API design

Production systems

Tools

FastAPI

Celery

SQL

Data pipelines

AWS

GCP

Docker

CI/CD

TypeScript

Node.js

Ruby on Rails

LangChain/LlamaIndex

Job description

Salary: $175,000 - $220,000 per year plus equity.

About the Role

This opportunity is for a Senior Backend Engineer responsible for building and owning AI-powered backend systems from rapid prototyping through production deployment and ongoing evaluation. The role focuses on developing APIs, tool-using LLM agents, retrieval-augmented generation (RAG) pipelines, and reliable backend services that power production AI applications.

You will work across backend engineering, AI infrastructure, evaluation systems, observability, and data pipelines while delivering scalable, production-ready AI capabilities. This is a high-ownership engineering role with significant influence over architecture, experimentation, reliability, and engineering best practices.

What You'll Do

Ship AI to Production

• Build tool-using LLM agents that support task planning, function calling, tool calling, multi-step workflows, guardrails, grant discovery, application drafting, and research assistance.
• Develop APIs, AI services, and retrieval-augmented generation (RAG) pipelines that power production AI applications.
• Transform prototypes into resilient, observable production services with clearly defined service-level objectives, rollback strategies, fallback mechanisms, and latency and cost controls.
• Develop evaluation frameworks and observability systems that keep AI services reliable, grounded, safe, and cost-effective.
• Write high-quality, thoroughly tested backend code and data pipelines supporting AI retrieval, evaluation, and production services.
• Develop scalable backend systems using Python and modern software engineering practices.
• Improve operational reliability through monitoring, alerting, dashboards, and incident response.

Collaborate and Raise Engineering Standards

• Partner with Product, Design, and Go-to-Market teams to define project scope, user experience, and success metrics.
• Design and execute experiments, including A/B testing and canary deployments, analyze results, and continuously improve AI features.
• Promote engineering excellence through maintainable code, automated testing, documentation, thoughtful code reviews, and scalable development practices.

Qualifications

Required

• 7+ years of experience designing, building, and deploying production backend systems using Python, FastAPI, Celery, or equivalent technologies.
• Experience delivering software from prototype to production using testing, observability, rollback strategies, and proven reliability practices.
• Hands-on experience building production LLM features, including tool calling, function calling, multi-step agent workflows, AI guardrails, and evaluation frameworks.
• Strong knowledge of SQL, database schema design, and data pipelines supporting retrieval and AI evaluation.
• Ability to thrive in a fast-paced startup environment with strong ownership, initiative, and a focus on speed, quality, and simplicity.

Preferred

• Experience with TypeScript and Node.js.
• Experience with Ruby on Rails or willingness to learn it.
• Experience using AWS or Google Cloud Platform (GCP).
• Experience with Docker, CI/CD pipelines, and production observability, including logs, metrics, and distributed tracing.
• Strong experience with retrieval-augmented generation (RAG), including document ingestion, chunking, windowing, embeddings, hybrid search, reranking, and grounded citations.
• Experience with rerankers, cross-encoders, hybrid retrieval optimization, search systems, or recommendation systems.
• Experience designing evaluation suites for retrieval, question answering, extraction, and summarization using both automated and human-in-the-loop evaluation methods.
• Familiarity with evaluation frameworks such as Ragas, DeepEval, or OpenAI Evals.
• Experience with AI orchestration frameworks, including LangChain, LangGraph, LlamaIndex, Semantic Kernel, or equivalent custom orchestration solutions.
• 100% employer-paid medical, dental, and vision insurance for employees.
• 50% employer-paid medical, dental, and vision insurance for eligible dependents.
• Generous paid time off, including parental leave.
• Company-provided laptop.
• Home office stipend.
• Company retreats held twice each year.
• Continuous opportunities for professional growth and new technical challenges.

Recruitment notice: all communication only happens from authorized email addresses ending [e-mail]. We never ask for payments or sensitive documents. Suspect a scam? Email [e-mail]