Software Engineer, AI

Calabrio•Toronto, ON

About The Position

Calabrio is looking for a highly skilled and experienced Software Engineer, AI to perform a key role in our digital transformation program, and deliver exceptional customer experience supported by trusted, and resilient business solutions. As an AI Software Engineer, you will design, build, deploy, and optimize AI-powered products and platforms, with a strong focus on LLM applications, agentic AI systems, applied machine learning, backend engineering, data pipelines, evaluation, and production operations. You will turn AI capabilities into reliable business solutions that are scalable, measurable, secure, and maintainable. This role is ideal for someone who can move beyond experimentation and deliver production-grade AI systems, including autonomous and semi-autonomous AI agents that can reason, plan, use tools, retrieve knowledge, and take actions safely within defined business workflows. Calabrio has embarked journey and is truly committed to establishing a value fabric that transforms its customer, employee, and stakeholder experiences through seamless integrated, agile, data-driven, and secure Digital Services. Such an endeavor requires leaders passionate about customer experience and committed to consistently delivering value while focusing on digital services with inherent trust and resilience.

Requirements

Problem solver - devise and implement advanced NLP algorithms and LLM models to address intricate challenges in Conversation Intelligence analytics
Strong team player – works with internal and external stakeholders to solve problems and actively incorporate input from various sources
Excellent communication skills and collaborative working style
Ability to think “out of the box”, strong critical thinking and analytical skills
Bachelor’s degree in Computer Science, Engineering, or a related field required.
3+ years of end-to-end experience training, evaluating, testing, deploying, and monitoring machine learning models in production.
Hands-on experience building applications with LLMs, prompt engineering, retrieval-augmented generation, structured outputs, and model evaluation.
Experience with frameworks or platforms for LLM and agent orchestration, such as LangChain, LangGraph, Strands AI, or equivalent architectures.
Experience designing or building AI agents that use planning, memory, tool calling, workflow orchestration, agent-to-agent and external system integration to complete multi-step tasks.
Strong experience with Python and backend frameworks such as Flask or Django for building production APIs and AI services.
Strong understanding of machine learning fundamentals and practical experience with NLP tasks such as text classification, NER, clustering, topic modeling, semantic search, and conversational AI.
Experience with fine-tuning LLMs and transformer-based models such as BERT, RoBERTa, ALBERT, and a solid understanding of tokenizers, embeddings, pre-trained models, and adaptation techniques.
Experience with SQL and NoSQL databases, vector databases or embedding stores, and data pipelines for AI applications.
Experience with model serving, observability, evaluation, error analysis, prompt/version management, and monitoring of AI systems in production.
Familiarity with Linux systems and standard software engineering practices including testing, CI/CD, APIs, and version control.

Nice To Haves

Master’s degree preferred.
Experience with AWS, Azure, or GCP
Experience with Docker and Kubernetes
Experience with ETL and Data Engineering projects
Experience with PostgreSQL, Snowflake, or MongoDB
Experience with Kubeflow, or Airflow

Responsibilities

Design AI systems
Build end-to-end AI solutions using machine learning, deep learning, NLP, and generative AI technologies.
Develop LLM-powered applications
Create applications using foundation models, prompt engineering, retrieval-augmented generation, structured outputs, function/tool calling, and agent workflows.
Build agentic AI solutions
Design and implement AI agents that can plan, reason through multi-step tasks, interact with external tools and APIs, retrieve relevant context, and execute actions within controlled business processes.
Develop multi-agent and orchestration workflows
Create orchestrated AI systems where multiple agents or components collaborate to solve complex tasks, with clear control flow, observability, and fallback handling.
Productionize models and AI agents
Deploy, monitor, and maintain AI/ML models and agentic systems in production environments with strong reliability, performance, and safety standards.
Build data and inference pipelines
Develop pipelines for ingestion, preprocessing, vector search, model inference, agent memory/context management.
Improve quality and evaluation
Define offline and online evaluation frameworks for model quality, latency, safety, task completion, agent reliability, and business outcomes.
Optimize performance and cost
Improve model selection, prompt efficiency, agent orchestration, latency, throughput, caching, token usage, and serving efficiency.
Ensure governance and safety
Apply best practices for security, privacy, responsible AI, model risk controls, guardrails, agent permissions, compliance, and human-in-the-loop review where needed.