Senior Java Backend Engineer – GenAI / LLM

Senior Java Backend Developer – Java 17+, Spring Boot, Microservices & GenAI/LLM

Toronto, ON - Hybrid (4 Days WFO)

Experience Required: 7+ years

Role Descriptions:

Key Responsibilities

• Design, develop, and maintain high-performance backend services using Java (17+), Spring Boot, and Microservices architecture.

• Build and expose RESTful and event-driven APIs supporting enterprise-scale applications.

• Integrate Generative AI / LLM capabilities (e.g., text generation, summarization, Q&A, classification) into backend workflows.

• Design, test, and optimize prompts and prompt orchestration strategies to ensure accuracy, determinism, and performance.

• Develop AI-aware backend components such as:

• Prompt templates and prompt pipelines

• Retrieval-Augmented Generation (RAG) services

• AI inference orchestration layers

• Implement secure API integrations with AI platforms and internal data sources, ensuring compliance with enterprise security standards.

• Apply prompt versioning, evaluation, and monitoring techniques to improve AI output quality over time.

• Ensure nonfunctional requirements: scalability, resiliency, performance, and observability.

• Contribute to CI/CD pipelines, containerization, and cloud-native deployments.

• Participate in code reviews, architecture discussions, and technical design decisions.

• Support production systems and troubleshoot complex backend or AI-integration issues.

Required Technical Skills

Core Backend Engineering

• 5+ years of strong hands-on experience in Java backend development.

• Expertise in Java 11/17+, Spring Boot, Spring MVC, Spring Security.

• Solid experience in Microservices, REST APIs, and API design (OpenAPI/Swagger).

• Experience with containers and cloud platforms (Docker, Kubernetes, OpenShift, Azure/AWS).

• Strong knowledge of SQL and NoSQL databases (e.g., DB2, PostgreSQL, MongoDB).

• Experience in CI/CD, DevOps practices, and automated testing.

AI & Prompt Engineering

• Hands-on experience integrating Large Language Models (LLMs) into backend systems.

• Strong understanding of prompt engineering techniques, including:

• Zero-shot, few-shot, and chain-of-thought prompting

• Prompt templates and dynamic prompt generation

• Guardrails, validation, and hallucination reduction

• Experience building RAG-based solutions using vector stores and embeddings.

• Familiarity with AI orchestration frameworks or SDKs (enterprise or open-source).

• Ability to evaluate prompt and model responses for quality, bias, and consistency.

Security & Compliance

• Experience implementing OAuth2.0, JWT, SSL/TLS, and secure API patterns.

• Awareness of data privacy, PII handling, and AI governance in regulated environments (BFSI preferred).