Python & Java AI Developer

Realign Llc; Toronto; Hybrid; CAD 110,000 - 170,000; Full time

Job summary

Realign Llc in Toronto, Ontario is seeking an experienced Python & Java AI Developer to drive an enterprise-wide Generative AI and agentic AI initiative in a regulated banking environment. The role requires delivering secure, scalable AI-enabled applications and collaborating with business, product, architecture, data, security, and engineering teams to achieve measurable business outcomes.

You will design, build, test, and productionize AI solutions, including conversational assistants, RAG

Qualifications

• Extensive hands-on Python and Java development experience.
• Experience building enterprise-grade AI and API/microservice applications.
• Hands-on experience with Generative AI and LLMs.
• Knowledge of RAG architectures.
• Experience with prompt engineering, embeddings, and retrieval.
• Experience designing agentic AI solutions and orchestration workflows.
• Ability to integrate AI/ML models with enterprise data sources.
• Strong understanding of REST APIs, CI/CD, and software engineering best practices.

Responsibilities

• Design, develop, test, deploy, and support AI-enabled enterprise applications using Python and Java.
• Develop Generative AI solutions including conversational assistants, RAG pipelines, enterprise search, summarization, and workflow automation.
• Build agentic AI capabilities using tool/function calling, orchestration, guardrails, human-in-the-loop controls, and auditable execution flows.
• Integrate Large Language Models (LLMs), machine learning models, APIs, vector stores, enterprise data sources, and existing applications.
• Develop scalable REST APIs and microservices using modern Python and Java frameworks.
• Implement prompt engineering, document chunking, embeddings, retrieval, reranking, grounded response generation, and output validation.
• Design and implement evaluation frameworks covering accuracy, groundedness, safety, latency, reliability, and cost.
• Automate regression testing and evaluation of AI model behavior and application responses.
• Implement MLOps and LLMOps practices including version control, CI/CD, containerization, model and prompt versioning, monitoring, and incident support.
• Apply privacy, security, identity and access management, responsible AI, and model-risk controls appropriate for a regulated banking environment.
• Partner with business and technical stakeholders to identify use cases, assess feasibility, define acceptance criteria, and demonstrate prototypes.
• Transition successful AI solutions from proof-of-concept into production-ready enterprise applications.
• Perform code reviews, troubleshoot complex technical issues, and document architecture and technical decisions.
• Mentor engineering team members and contribute to development standards and best practices.

Skills

Python

Java

Generative AI

Agentic AI

LLM/RAG

AI Engineering

Job description

Job Type: Full Time
Location: Toronto, ON
Work Model: Hybrid – 4 Days Onsite

Primary Skills

Python & Java, Generative AI & Agentic AI, LLM/RAG & AI Engineering

Job Description

We are seeking an experienced Python & Java AI Developer to support an enterprise-wide Generative AI and Agentic AI initiative within a regulated banking environment. The successful candidate will combine strong Python and Java software engineering expertise with hands‑on experience designing and implementing secure, scalable AI, Generative AI, and agentic solutions.

The role will support the complete AI solution lifecycle, from use-case discovery and prototyping through production implementation and support. The developer will collaborate closely with business, product, architecture, data, security, and engineering teams to deliver measurable business outcomes.

Key Responsibilities

• Design, develop, test, deploy, and support AI-enabled enterprise applications using Python and Java.
• Develop Generative AI solutions including conversational assistants, RAG pipelines, enterprise search, summarization, and workflow automation.
• Build agentic AI capabilities using tool/function calling, orchestration, guardrails, human-in-the-loop controls, and auditable execution flows.
• Integrate Large Language Models (LLMs), machine learning models, APIs, vector stores, enterprise data sources, and existing applications.
• Develop scalable REST APIs and microservices using modern Python and Java frameworks.
• Implement prompt engineering, document chunking, embeddings, retrieval, reranking, grounded response generation, and output validation.
• Design and implement evaluation frameworks covering accuracy, groundedness, safety, latency, reliability, and cost.
• Automate regression testing and evaluation of AI model behavior and application responses.
• Implement MLOps and LLMOps practices including version control, CI/CD, containerization, model and prompt versioning, monitoring, and incident support.
• Apply privacy, security, identity and access management, responsible AI, and model‑risk controls appropriate for a regulated banking environment.
• Partner with business and technical stakeholders to identify use cases, assess feasibility, define acceptance criteria, and demonstrate prototypes.
• Transition successful AI solutions from proof‑of‑concept into production‑ready enterprise applications.
• Perform code reviews, troubleshoot complex technical issues, and document architecture and technical decisions.
• Mentor engineering team members and contribute to development standards and best practices.

Required Skills & Experience

• Strong hands‑on experience with Python and Java development.
• Experience building enterprise‑grade applications, APIs, and microservices.
• Hands‑on experience with Generative AI and Large Language Models (LLMs).
• Strong understanding of Retrieval‑Augmented Generation (RAG) architectures.
• Experience with prompt engineering, embeddings, vector search, retrieval, reranking, and response validation.
• Experience designing or implementing Agentic AI solutions and orchestration workflows.
• Experience integrating AI/ML models with enterprise applications and data sources.
• Strong understanding of REST APIs, microservices, CI/CD, and software engineering best practices.
• Knowledge of AI evaluation, testing, monitoring, reliability, and cost optimization.
• Understanding of security, privacy, responsible AI, and governance requirements.

Preferred Skills

• Experience with Azure AI Services, Azure OpenAI, Azure AI Search, or comparable cloud AI platforms.
• Experience with LangChain, Semantic Kernel, LlamaIndex, PyTorch, TensorFlow, or scikit‑learn.
• Knowledge of agentic AI patterns, Model Context Protocol (MCP), and multi‑agent orchestration.
• Experience with enterprise knowledge platforms and vector databases.
• Experience implementing AI governance, responsible AI controls, privacy safeguards, content safety, and model‑risk documentation.
• Experience with GitHub Copilot or other AI‑assisted development tools.
• Experience with Docker, Kubernetes, and cloud‑native application development is an advantage.

Banking & Regulatory Experience

• Prior experience in the Banking or Financial Services domain is preferred.
• Understanding of security, audit, compliance, privacy, and data‑governance requirements in regulated environments.
• Experience developing enterprise solutions that meet organizational security and risk‑management standards.

MLOps & LLMOps

• Implement model and prompt versioning and lifecycle management.
• Build CI/CD pipelines for AI‑enabled applications.
• Implement monitoring for model performance, application reliability, latency, safety, and cost.
• Support production incidents and continuous improvement of AI solutions.
• Establish automated evaluation and regression‑testing processes for AI behavior.
• Work closely with business stakeholders, Product Owners, Architects, Data Scientists, Security teams, and Engineering teams.
• Participate in Agile ceremonies, sprint planning, code reviews, demonstrations, and retrospectives.
• Translate business requirements into scalable AI and software solutions.
• Clearly communicate technical concepts and AI capabilities to both technical and non‑technical stakeholders.