Hybrid AI Engineer

at Aspire Software

• Job title: AI Engineer
• Job type: Full Time
• Experience level: Mid level, Senior
• Salary: Not specified
• Degree requirement: Bachelor's Degree
• Tech skills: AWS, Azure, JavaScript, Microservices, NoSQL, Postgres, Python, SQL
• Location requirements: Hybrid, Montreal, Canada

About the role

• Senior AI Software Engineer developing AI products for Valsoft Corporation. Leading the design and implementation of AI solutions while collaborating with engineers and product teams.

Responsibilities

• Drive the development and launch of new AI-powered products — from concept and prototype to market-ready release — with a focus on rapid iteration and measurable impact.
• Operate with a startup mindset: bias toward action, ownership across the full stack, and the ability to turn ambiguity into execution.
• Build scalable systems that not only attract new customers but also deepen adoption and upsell opportunities across our existing base.
• Build RESTful APIs, microservices, front and back-end components using a polyglot approach (Python, JavaScript frameworks)
• Develop context strategies (e.g., embeddings, retrieval augmentation, windowing) for reliability, security, and cost efficiency
• Apply evaluation frameworks (Promptfoo, OpenAI Evals, LangSmith) to systematically test, compare, and validate LLM outputs
• Build and tune AI models, assistants, agentic workflows, vector databases.
• Work closely with senior engineers and product owners to clarify requirements and deliver solutions that add measurable business value
• Work closely with other teams to design interfaces and get them implemented for consumption by AI tooling and products.
• Mentor engineers on prompt design, evaluation best practices, and context strategies
• Participate in sprint planning, code reviews, and backlog grooming.
• Integrate regression and adversarial testing into CI/CD pipelines to prevent prompt drift
• Define automated evaluation suites for LLM applications (truthfulness, consistency, compliance)
• Support efforts to reduce technical debt and improve maintainability.
• Experiment with and apply Generative AI and ML tools where they can accelerate development or improve user experience
• Create, optimize, and manage complex prompt strategies to maximize AI model performance
• Develop reusable prompt templates for consistent outputs across multiple use cases
• Design and optimize NLQ interfaces that let users query enterprise data (SQL/NoSQL, APIs, vector stores) in natural language, applying context engineering and evaluation frameworks to ensure accuracy, security, and business relevance.
• Troubleshoot and optimize performance, scalability, and data-handling issues
• Adapt to different technical environments across the portfolio.

Requirements

• 5–8 years of professional software engineering experience with Python and JavaScript frameworks
• Hands-on expertise with Generative AI and ML tools (Promptfoo, OpenAI Evals, LangSmith, LangChain, AWS Bedrock, Azure AI, etc.) is a must
• Familiarity with vector databases (e.g., PostgreSQL/pgvector, Pinecone, Weaviate, Milvus) and RAG (Retrieval-Augmented Generation) pipelines is preferred
• Deep and recent experience with Generative AI or machine learning development tools (Claude Code, Github Copilot, AWS Bedrock, OpenAI, LangChain, Azure AI, etc.) is preferred
• Proven ability to design and implement NLQ solutions enabling users to query structured/unstructured data sources conversationally, with focus on accuracy, performance, and security.
• Familiarity with Git-based workflows and CI/CD pipelines.
• Collaborative mindset with strong communication skills
• Comfortable working in a remote, distributed environment
• Willingness to learn, experiment, and take initiative.

Benefits

• Competitive compensation package
• Performance-based bonus potential
• Comprehensive benefits package
• Hybrid or Fully remote work environment