Senior Generative AI Engineer (LLM / RAG / MLOps)

Hiring: Senior Generative AI Engineer (LLM / RAG / MLOps)

Location: Mississauga, Canada (Hybrid)

About the Role

We are seeking Senior Generative AI Engineers with strong hands-on experience in building and deploying LLM-powered, enterprise-grade applications. This role requires deep expertise in RAG pipelines, prompt engineering, and production-level AI systems, not just foundational knowledge.

Key Responsibilities

Design and implement scalable LLM-based applications for enterprise use cases

Build, optimize, and maintain advanced RAG (Retrieval-Augmented Generation) pipelines

Develop and refine prompt engineering strategies, prompt templates, and prompt tuning techniques

Implement agentic workflows and orchestration frameworks

Work with LangChain, LlamaIndex, or equivalent frameworks for LLM application development

Integrate AI solutions with enterprise systems using APIs, vector databases, and orchestration tools

Ensure model evaluation, observability, and performance monitoring

Implement security, privacy, and guardrails for GenAI applications

Deploy models into production using robust MLOps and CI/CD pipelines

Collaborate with cross-functional teams to deliver high-quality, scalable AI solutions

Required Skills & Experience

✅ Experience

8–10 years of experience in Software Engineering / AI/ML / Systems Development

Proven experience building production-grade GenAI solutions (Critical)

Generative AI & LLM Expertise (Critical)

Strong hands-on experience with LLMs (OpenAI, Gemini, Claude, Llama, Mistral, etc.)

Deep expertise in:

RAG pipelines (must-have, advanced level)

Prompt engineering, tuning, and prompt patterns

Agentic workflows and multi-step reasoning systems

Experience with evaluation frameworks, observability, and LLM performance tuning

Programming & Frameworks

Strong proficiency in Python (Mandatory)

Hands-on experience with:

LangChain, LlamaIndex (or equivalent)

ML/AI libraries: PyTorch, TensorFlow, Transformers

Data libraries: Pandas, NumPy, scikit-learn

API frameworks: FastAPI

Data & Retrieval

Strong experience with:

Vector databases (Pinecone, PGVector, MongoDB Atlas, Neo4j)

Retrieval strategies and hybrid search techniques

Ability to handle large-scale unstructured data pipelines

Deployment & MLOps (Critical)

Hands-on experience deploying LLM/GenAI models into production

Strong understanding of:

MLOps principles, model lifecycle, and monitoring

CI/CD pipelines (Jenkins, GitLab CI, Azure DevOps, ArgoCD)

Cloud & Infrastructure

Experience with:

Cloud platforms (AWS, GCP, Azure)

Kubernetes / OpenShift for container orchestration

Security & Governance

Understanding of:

AI safety, guardrails, and responsible AI practices

Data privacy and secure AI system design

What We’re Looking For

Candidates with hands-on, real-world implementation experience (not just theoretical knowledge)

Strong ability to design and deliver enterprise-scale AI systems

Proven track record of working on complex, production-grade GenAI use cases