Onsite_Backend Engineer – Agentic AI & LLM Systems in AZ

Themesoft Inc; Phoenix (AZ); On-site; USD 140,000 - 190,000; Full time

Job summary

Themesoft Inc in Phoenix, AZ is seeking a Senior Backend Engineer to design, develop, and maintain scalable backend services and autonomous AI workflows. You will own shared agentic AI capabilities and drive architectural decisions for multiple products.

Expertise in Node.js, TypeScript and/or Go, distributed systems, and cloud infrastructure is essential. You will lead design reviews, build RAG pipelines, and ensure observability, security, and cost efficiency in production.

Qualifications

• 10–12 years of overall software engineering experience, with substantial experience building large-scale distributed systems.
• Proven ownership of complex, cross-functional agentic AI systems spanning multiple teams or products.
• Demonstrated ability to influence technical architecture and deliver production-ready systems.

Responsibilities

• Design, develop, and maintain high-performance backend services, REST APIs, and microservices for scalable applications.
• Architect, build, and operate production-grade agentic AI systems and shared capabilities used across multiple products and teams.
• Drive technical direction for agentic AI initiatives, defining architecture patterns, autonomy boundaries, and system design principles.
• Design and implement agent frameworks, orchestration layers, planning mechanisms, tool integration, memory management, and evaluation strategies.
• Develop Retrieval-Augmented Generation (RAG) pipelines to improve information retrieval and grounding.
• Build and optimize LLM infrastructure, model gateways, inference pipelines, and related AI platform capabilities.
• Implement observability, evaluation, monitoring, and safety mechanisms for autonomous AI systems.
• Design and optimize distributed, event-driven architectures using Kafka, queues, and streaming systems.
• Collaborate with DevOps and platform teams to deploy and monitor services in AWS and GCP.

Skills

Node.js

TypeScript

Go

REST APIs

Distributed systems

Cloud (AWS/GCP)

Kafka

Docker

Kubernetes

PostgreSQL

NoSQL (MongoDB, Redis)

CI/CD

Education

Bachelor's degree in Computer Science or related

Master's degree preferred

Tools

LangGraph

LangChain

AWS

GCP

Apache Kafka

Docker

Kubernetes

Job description

Job Id : OOJ - 27570

Posted Date : 10/14/2026

Experience : -

Job Type : Contractual

Location : Phoenix, AZ

Overview

Title: Senior Backend Engineer – Agentic AI & LLM Systems
Location: Phoenix, AZ (Onsite)
Work Arrangement: Onsite
Employment Type: Contract
Duration: 6 Months
Primary Skills: Agentic AI, LLM, Rest API
Job Summary

We are seeking an experienced Senior Backend Engineer specializing in Agentic AI and Large Language Model (LLM) systems to design, develop, and maintain scalable, high-performance backend services and production-grade autonomous AI systems. The ideal candidate will have strong expertise in Node.js, TypeScript and/or Go, distributed systems, cloud infrastructure, and agentic AI workflows. The role involves owning shared agentic AI capabilities across multiple products, driving architectural decisions, and delivering reliable, secure, and cost-effective autonomous systems. The candidate will collaborate with cross-functional teams to establish technical direction, improve system performance, and translate complex business requirements into scalable engineering solutions.

Key Responsibilities

• Design, develop, and maintain high-performance backend services, REST APIs, and microservices for scalable applications.
• Architect, build, and operate production-grade agentic AI systems and shared capabilities used across multiple products and teams.
• Drive technical direction for agentic AI initiatives, defining architecture patterns, autonomy boundaries, and system design principles.
• Design and implement agent frameworks, orchestration layers, planning mechanisms, tool integration, memory management, and evaluation strategies.
• Develop Retrieval-Augmented Generation (RAG) pipelines to improve information retrieval, contextual grounding, and response quality.
• Build and optimize LLM infrastructure, model gateways, inference pipelines, and related AI platform capabilities.
• Implement observability, evaluation, monitoring, and safety mechanisms to ensure the reliability and responsible operation of autonomous AI systems.
• Design and optimize distributed, event-driven architectures using technologies such as Apache Kafka, asynchronous processing, queues, and streaming systems.
• Optimize backend systems for performance, scalability, reliability, availability, and cost efficiency under high workloads.
• Lead technical design reviews and guide engineering teams through architectural trade-offs involving autonomy, safety, scalability, reliability, and cost.
• Collaborate with DevOps and platform teams to deploy, manage, and monitor services in cloud environments such as AWS and Google Cloud Platform (GCP).
• Implement engineering best practices for code quality, automated testing, version control, CI/CD, and deployment automation.
• Work closely with frontend engineers and cross-functional stakeholders to define API contracts and ensure seamless system integration.
• Influence technical decisions and align teams across multiple products without requiring formal managerial authority.
• Troubleshoot complex technical issues and deliver reliable solutions in ambiguous and evolving problem spaces.

Required Technical Skills

Backend Development

• Strong proficiency in Node.js, JavaScript, TypeScript, and/or Go (Golang).
• Extensive experience designing and developing RESTful APIs, microservices, and scalable backend applications.
• Strong understanding of backend architecture, system design, data pipelines, and software engineering fundamentals.

Agentic AI and LLM Systems

• Strong experience building and deploying LLM-powered applications, agentic workflows, or advanced machine learning infrastructure.
• Deep understanding of agentic AI concepts, including planning, tool use, memory, orchestration, and evaluation.
• Hands‑on experience with frameworks such as LangGraph, LangChain, and similar agent orchestration technologies.
• Experience designing RAG pipelines, retrieval and grounding mechanisms, and LLM integration patterns.
• Understanding of LLM inference, model gateways, evaluation frameworks, observability, and AI safety practices.
• Familiarity with AI‑assisted software development and agentic development workflows.

Cloud and Infrastructure

• Hands‑on experience with AWS and/or Google Cloud Platform (GCP).
• Experience with Docker, Kubernetes, and containerized application deployment.
• Strong understanding of cloud‑native architecture, infrastructure scalability, and production operations.

Distributed Systems and Messaging

• Experience designing distributed systems and event-driven architectures.
• Hands‑on experience with Apache Kafka or similar messaging and streaming platforms.
• Knowledge of workflow engines, asynchronous processing, queues, and streaming systems.

Databases and DevOps

• Proficiency in SQL and relational databases such as PostgreSQL.
• Experience with NoSQL and in-memory data stores such as MongoDB and Redis.
• Experience with Git, CI/CD pipelines, automated testing, and deployment practices.

Education and Experience

• Bachelor's degree in Computer Science, Engineering, or a related field.
• Master's degree preferred.
• 10–12 years of overall software engineering experience, with substantial experience building large-scale distributed systems.
• Proven ownership of complex, cross‑functional agentic AI systems spanning multiple teams or products.
• Demonstrated ability to influence technical architecture, guide engineering decisions, and deliver production‑ready systems.
• Excellent problem‑solving, communication, collaboration, and technical leadership skills.

Preferred Qualifications

• Experience building agentic AI systems in fintech or other regulated industries.
• Experience as a founding engineer or early technical leader in AI-driven products.
• Demonstrated success delivering technically complex autonomous systems in production environments.
• Meaningful contributions to open‑source AI, LLM, or agentic frameworks.
• Familiarity with model fine‑tuning, model optimization, and inference pipelines.
• Experience balancing AI system autonomy with security, reliability, safety, performance, and operational cost.

Work Authorization

Applicants must be legally authorized to work in the United States.

Equal Employment Opportunity

Themesoft Inc is an Equal Employment Opportunity employer. We consider qualified applicants without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other status protected by applicable federal, state, or local law.