Backend Software Engineer – GenAI

CyRAD Talent Solutions; Arlington (VA); On-site; USD 190,000 - 240,000; Full time

Benefits offered by this job

Equity

Sign-on bonus

Job summary

CyRAD Talent Solutions is hiring a backend engineer to own production GenAI systems at a fast-scaling AI software company. You’ll design retrieval architectures, integrate LLMs, and build reliable APIs and distributed services for real-world use.

This role emphasizes ownership, architecture decisions, and end-to-end delivery rather than prototyping. You'll work alongside engineers and domain experts in a fast-moving environment, evaluating AI behavior, building testing infra, and iterating on

Qualifications

• 6+ years of software engineering experience with a backend foundation.
• Hands-on experience building and shipping production GenAI or LLM systems (required).
• Experience with RAG, vector databases, LLM integrations, evaluation systems, and tool calling.
• Strong understanding of distributed systems, APIs, and production-grade software.
• Working understanding of how modern AI systems behave and how to evaluate them.
• Strong ownership mentality in a fast-moving environment.
• Ability to work onsite in Arlington, VA or Seattle, WA.

Responsibilities

• Design and deploy RAG architectures, vector search, LLM integrations, and agentic or tool-calling systems for production use.
• Build reliable APIs, distributed systems, and backend services that support AI-powered products.
• Develop evaluation and testing systems to measure output quality and catch regressions before they ship.
• Take systems from architecture through deployment and iterate based on real-world performance.
• Contribute to architecture decisions, code reviews, and engineering standards across the team.

Skills

Backend development

GenAI/LLM systems

RAG architectures

Vector databases

APIs & distributed systems

Ownership mentality

On-site work

Tools

AWS

Kubernetes

Job description

Location: Arlington, VA or Seattle, WA
Work Model: Onsite
Compensation: $190K to $240K base + equity + sign-on bonus

Overview

A fast-scaling technology company building AI-enabled software for high-consequence operational environments is hiring a backend engineer to own production GenAI systems. This is engineering work at the systems level: retrieval architectures, LLM integrations, agentic tool-calling, and the APIs and distributed services that make them dependable under real operating conditions. The work is not prototypes or thin wrappers around third-party models.

The role carries meaningful ownership over architecture and implementation. Systems move from design through production and then keep improving based on how they actually perform in use. A central part of the job is building the evaluation and testing infrastructure that measures output quality, surfaces failure modes, and prevents regressions, so that AI behavior can be trusted in settings where mistakes carry consequences.

The position sits alongside experienced engineers, product leaders, and domain experts in a fast-moving environment, and is well suited to someone who wants to influence engineering decisions rather than execute a fixed spec.

What You’ll Do

• Design and deploy RAG architectures, vector search, LLM integrations, and agentic or tool-calling systems for production use
• Build reliable APIs, distributed systems, and backend services that support AI-powered products
• Develop evaluation and testing systems to measure output quality, identify failure modes, and catch regressions before they ship
• Take systems from architecture through deployment and iterate on them based on real-world performance
• Contribute to architecture decisions, code reviews, and engineering standards across the team

What We’re Looking For

• 6+ years of software engineering experience with a strong backend foundation
• Hands-on experience building and shipping production GenAI or LLM systems (required, not experimental or side-project exposure)
• Experience with some combination of RAG, vector databases, LLM integrations, evaluation systems, and tool calling
• Strong understanding of distributed systems, APIs, and production-grade software
• A working understanding of how modern AI systems behave, where they fail, and how to evaluate them
• Strong ownership mentality and the ability to operate effectively in a fast-moving environment
• Ability to work onsite in Arlington, VA or Seattle, WA

Preferred

• Experience with agentic AI systems, model evaluation, or fine-tuning
• Experience with AI infrastructure, embedding pipelines, or inference optimization
• Deployment experience across AWS, Kubernetes, cloud, or edge environments
• Background building software for complex operational or mission-critical environments

Compensation

$190K to $240K base salary, plus equity with a potentialsign-on bonus.