AI Engineer, Back End

OSI Engineering; Menlo Park (CA); On-site; USD 180,000 - 195,000; Full time

Job summary

OSI Engineering in Menlo Park, CA is seeking an experienced Software Engineer to drive backend services powering generative AI capabilities across product suites. You will design cloud-based AI infrastructure, implement robust JVM-based systems in Kotlin/Java, and ensure secure, observable, production-grade services.

You will collaborate with cross-functional teams to translate AI concepts into scalable APIs, orchestrate tools and MCP services, and mentor junior engineers while prioritizing

Qualifications

• 8+ years of software engineering experience, including SaaS/PaaS products.
• 5+ years with Java or Kotlin, Spring Framework, and AWS.
• 3+ years in microservices, REST + JSON, and reactive programming.
• Experience with LLM-backed features, streaming patterns, and tool calling.
• Familiarity with ORM (Hibernate/JPA) and SQL databases.

Responsibilities

• Deliver production-grade backend servers in Kotlin/Java.
• Collaborate with cross-functional teams to implement AI features.
• Build and evolve secure, observable cloud services and APIs.
• Mentor junior engineers and ensure code quality and security.
• Leverage AI coding tools to accelerate development and testing.

Skills

Backend engineering

Kotlin/Java

Cloud services

APIs & integration

Mentoring

Education

BS/MS in Computer Science/Engineering

Tools

Java

Kotlin

Spring Framework

AWS

Hibernate/JPA

REST APIs

Project Reactor / WebFlux

Kotlin Coroutines

Job description

We’re looking for an experienced Software Engineer to be a key contributor in developing the backend services that power generative AI functionality across the family of products. You will design and implement cloud-based AI service infrastructure for conversational experiences, retrieval-augmented generation, tool orchestration, MCP services, memory and persistence systems, and model integration. This role requires strong backend engineering judgment, strong JVM backend experience, preferably with Kotlin and Java, and the ability to turn fast-moving AI capabilities into secure, scalable, observable, production-ready services.

Responsibilities

• Deliver high-quality, scalable, production-ready backend/server code in Kotlin and Java Cloud Services by implementing best practices in software engineering, including coding standards, testing and deployment procedures.
• Partner closely with a cross-functional team of key stakeholders (Engineers, Architects, Product Managers, QA, Operations, and Business Partners) to translate AI product concepts into robust backend systems.
• Build and evolve APIs that allow product teams to safely integrate AI functionality across web, mobile, and desktop experiences.
• Design and implement tool-calling and MCP services that support reliable multi-step workflows, secure execution, and permissioned access to user data from AI-powered product experiences.
• Build production-grade AI infrastructure with strong attention to latency, cost, observability, failure handling, privacy, and security.
• Mentor junior developers using expertise in software development methodology and frameworks, in areas such as quality, security, and scalability.
• Effectively leverage AI coding assistants (Claude, Codex, etc.) to accelerate implementation, code review, and testing, while applying strong engineering judgment to validate the correctness, security, and maintainability of AI-generated code.

Qualifications

• 8+ years of software engineering experience, including a successful track record developing customer-facing SaaS/PaaS products.
• 5+ years working experience in Java or Kotlin, Spring Framework, and AWS.
• 3+ years working experience within microservice architecture, specifically utilizing REST services and JSON.
• Experience with reactive programming on the JVM, such as Project Reactor, Spring WebFlux, RxJava, Kotlin coroutines, or Kotlin Flow.
• Hands-on experience building or integrating LLM-backed product functionality, including streaming response patterns such as SSE, cancellation, timeouts, and fallback handling.
• Experience with conversation state management, persistence models, memory systems, prompt orchestration, and tool/function calling.
• Experience with RAG patterns, embeddings, vector databases, retrieval quality, grounding, and evaluation.
• Hands-on experience integrating AI coding tools (e.g., Claude Code, GitHub Copilot, Codex) into the SDLC — comfortable using them for scaffolding, refactoring, and test generation, and skilled at critically reviewing their output rather than accepting it blindly.
• Familiarity with model customization techniques, including fine-tuning, prompt/version management, structured outputs, and model evaluation.
• Excellent understanding of O/R mapping concepts and tools (Hibernate, JPA).
• Fluent in Databases/SQL (MySQL experience preferred).
• Excellent programming discipline: data structures, complexity analysis, object-oriented principles, design patterns, and unit testing.
• Experience mentoring junior engineers.
• BS/MS in Computer Science/Engineering or equivalent.

Type: Full Time

Salary Range: $180K - $195K base + bonus/equity