Backend AI Engineering Lead

Harnham; United States; On-site; USD 180,000 - 280,000; Full time

Job summary

Harnham is seeking a Backend AI Engineering Lead to design and build production-grade AI-powered applications and services.

The role centers on a strong Java foundation and hands-on work with LLMs, generative AI, and agentic architectures across the full AI project lifecycle, from prototype to production deployment.

Qualifications

• 10+ years of professional software engineering experience.
• Strong backend engineering experience with modern application architectures.
• Experience with Spring Boot, REST APIs, and microservices.
• Demonstrated experience building or integrating AI/ML capabilities into software products.
• Experience taking projects from prototype through production.
• Experience working with existing production platforms and codebases.
• Strong understanding of software architecture and distributed systems.

Responsibilities

• Design and develop scalable backend services and AI-powered applications, primarily using Java.
• Build and integrate applications using LLMs, generative AI, and agentic architectures.
• Design AI workflows capable of interacting with APIs, tools, services, and external systems.
• Develop RAG-based applications, retrieval workflows, and intelligent search capabilities.
• Integrate LLM APIs and AI services into existing software platforms.
• Design backend APIs and services that support AI-powered products and workflows.
• Take AI concepts and prototypes through technical validation, implementation, and production deployment.
• Evaluate emerging AI technologies and frameworks and determine how they can be applied to real-world engineering problems.
• Work with existing production systems and integrate new AI capabilities without compromising reliability or maintainability.
• Design solutions with scalability, security, performance, observability, and reliability in mind.
• Collaborate with engineering and product stakeholders to translate ambiguous requirements into practical technical solutions.
• Provide technical leadership through architecture, design reviews, code reviews, and mentoring.
• Help establish engineering patterns and best practices for building production AI applications.

Skills

Backend engineering

Java

REST APIs

Microservices

AI/ML integration

Distributed systems

CI/CD

Security

Observability

Prototyping to production

Tools

Spring Boot

LangChain

LlamaIndex

LangGraph

LangChain4j

Job description

We’re looking for a Backend AI Engineering Lead to design and build production-grade AI-powered applications and services.

This is a hands-on engineering role for an experienced backend engineer with a strong Java foundation and practical experience building applications around LLMs, generative AI, and agentic systems.

You’ll work across the full lifecycle of AI initiatives — from exploring new technologies and developing prototypes through architecture, implementation, integration, and production deployment.

The ideal candidate combines strong software engineering fundamentals with the ability to translate emerging AI capabilities into scalable, reliable, production-ready applications.

What You’ll Do

• Design and develop scalable backend services and AI-powered applications, primarily using Java.
• Build and integrate applications using LLMs, generative AI, and agentic architectures.
• Design AI workflows capable of interacting with APIs, tools, services, and external systems.
• Develop RAG-based applications, retrieval workflows, and intelligent search capabilities.
• Integrate LLM APIs and AI services into existing software platforms.
• Design backend APIs and services that support AI-powered products and workflows.
• Take AI concepts and prototypes through technical validation, implementation, and production deployment.
• Evaluate emerging AI technologies and frameworks and determine how they can be applied to real-world engineering problems.
• Work with existing production systems and integrate new AI capabilities without compromising reliability or maintainability.
• Design solutions with scalability, security, performance, observability, and reliability in mind.
• Collaborate with engineering and product stakeholders to translate ambiguous requirements into practical technical solutions.
• Provide technical leadership through architecture, design reviews, code reviews, and mentoring.
• Help establish engineering patterns and best practices for building production AI applications.

Must Have

• 10+ years of professional software engineering experience
• Strong backend engineering experience with modern application architectures
• Experience with Spring Boot, REST APIs, and microservices
• Demonstrated experience building or integrating AI/ML capabilities into software products
• Experience taking projects from prototype through production
• Experience working with existing production platforms and codebases
• Strong understanding of software architecture and distributed systems
• Strong software engineering fundamentals across:
• Automated testing
• CI/CD
• Security
• Monitoring and observability
• Performance and scalability
• Working knowledge of SQL and data-driven applications
• Strong communication and technical problem-solving skills
• Comfortable operating as a hands-on technical leader

Generative AI & Agentic Engineering

Hands-on experience with several of the following:

• RAG and retrieval-based systems
• Vector databases and semantic search
• Agentic AI architectures
• Tool and function calling
• AI agents interacting with APIs and external systems
• Prompt and context engineering
• LLM orchestration frameworks
• AI observability and monitoring
• AI security and guardrails
• Model inference and integration

Experience with frameworks such as LangChain, LangGraph, LlamaIndex, Spring AI, LangChain4j, or comparable technologies is valuable.

Additional Technical Experience

Experience with one or more of the following is beneficial:

• Python
• FastAPI
• Event-driven architectures
• Distributed systems
• Data pipelines and data services
• Model deployment and inference
• AI evaluation frameworks

What We’re Looking For

The strongest candidates will be experienced backend engineers who have moved into applied AI engineering.

You should be able to take an ambiguous AI use case, determine the appropriate technical approach, build the underlying application and integrations, and ultimately deliver a production-quality solution.

This is not a pure research role and does not require a traditional ML research background. The focus is on software engineering + applied AI + production delivery.

You’ll have significant ownership across the intersection of backend architecture, generative AI, LLM applications, and agentic systems.