Gen AI Developer Specialist

HEXAWARE•Canada,

About The Position

This role focuses on designing and building end-to-end AI-powered applications, integrating Large Language Models (LLMs) and agentic AI components into various workflows. The specialist will develop APIs and services for agent orchestration, tool calling, and workflow execution, as well as build intuitive user interfaces for AI-assisted workflows and monitoring. A key aspect involves operationalizing models and agentic systems into production, implementing Retrieval-Augmented Generation (RAG) pipelines, vector search, and AI inference layers. The role also encompasses managing the model lifecycle, building safeguards for AI-driven workflows, owning CI/CD pipelines, containerization, and deployment of AI applications. Ensuring systems meet performance, scalability, security, and reliability requirements, including logging, monitoring, and alerting, is crucial. Collaboration with platform, security, product, and business teams is expected, along with contributing to system architecture and mentoring other engineers.

Requirements

7+ years of hands-on experience as a Full Stack Engineer or Senior Software Engineer.
Strong proficiency in backend development Python.
Strong experience with modern frontend frameworks React.
Hands-on experience integrating AI/ML or LLM-based services into applications.
Solid understanding of REST APIs, microservices, and distributed systems.

Responsibilities

Design and build end-to-end AI-powered applications using modern frontend and backend frameworks.
Integrate LLM and agentic AI components into user-facing and system-facing workflows.
Develop APIs and services that support agent orchestration, tool calling, and workflow execution.
Build intuitive UIs for AI-assisted workflows, human-in-the-loop interactions, and monitoring.
Work with ML/Data teams to operationalize models and agentic systems into production.
Implement RAG pipelines, vector search integration, and AI inference layers.
Handle model lifecycle concerns: versioning, configuration, evaluation hooks, and rollout strategies.
Build safeguards, validations, and fallback mechanisms for AI-driven workflows.
Own CI/CD pipelines, containerization, and deployment of AI applications.
Ensure systems meet performance, scalability, security, and reliability requirements.
Implement logging, monitoring, alerting, and cost visibility for AI and application components.
Collaborate with platform and security teams to ensure compliance and operational readiness.
Contribute to system and application architecture decisions for AI platforms.
Write clean, maintainable, well-tested code and review contributions from peers.
Mentor engineers and raise the bar on engineering and AI delivery practices.
Partner with product and business teams to translate requirements into technical solutions.