Senior AI/ML Engineer – Agentic AI

About the job
JD-2025-AIML-1: Senior AI/ML Engineer – Agentic AI

Location: Toronto, ON (Hybrid)

Client: Applab/Loblaws

Type: Full-time Team: Machine Learning Platform / Digital & Data

About the Role

Loblaws Digital is hiring a Senior AI/ML Engineer with a strong emphasis on Agentic AI systems. This role focuses on building production-grade multi-agent workflows, LLM-powered automation, and scalable ML infrastructure on GCP. You will work on next-generation AI capabilities including Agentic AI, LangGraph-based pipelines, RAG architectures, and enterprise ML platforms supporting real-world retail and supply chain use cases. This is a high-priority hire and we are moving fast.

MUST-HAVE Requirements (Non-Negotiable)

Candidates must have all the following:

Agentic AI & LLM Development
Hands-on experience building Agentic AI systems using:
LangGraph (mandatory)
LangChain / LangSmith / LangServe
Multi-agent orchestration & tool calling
Proven experience deploying LLM applications in production (not just POCs).
Expertise in RAG pipelines, vector DBs (FAISS, Pinecone, Chroma, pgvector), memory models.
Strong skills in Prompt Engineering, LLM evaluation (RAGAS/TruLens), context optimization.
Engineering & Cloud
Advanced Python development for AI systems (FastAPI, async workflows, microservices).
Hands-on production experience with GCP:
Vertex AI
BigQuery
BigTable
Cloud Storage
Cloud Composer (Airflow)
Deep understanding of ML Ops / LLMOps:
CI/CD (GitHub Actions, Cloud Build, Jenkins)
Model deployment best practices
Docker, Kubernetes
Experience building end-to-end ML pipelines: ingestion → feature engineering → training → deployment

Experience Level

5+ years of ML/AI engineering
2+ years specifically with LLMs / Agentic AI
Experience working in enterprise or production-scale environments

What You’ll Do:

Agentic AI & LLM Engineering (Primary Focus)

Build multi-agent AI workflows using LangGraph and advanced orchestration patterns.
Implement RAG pipelines, long-term memory, and LLM-driven automation for enterprise workflows.
Fine-tune, evaluate, and optimize LLMs for low latency and high reliability in production

ML Platform & Infrastructure

Architect and maintain scalable ML/LLM infrastructure on GCP.
Integrate ML workflows via Cloud Composer (Airflow) and standardized pipelines.
Develop LLMOps foundations including model monitoring, drift detection, evaluation frameworks.
Cloud, Data & Platform Engineering

· Optimize cloud compute/storage for performance and cost.
· Build automated, self-service tooling for Data Scientists and ML Engineers.
Implement observability: tracing, logging, monitoring, and failover strategies.
Soft Skills & Team Fit

Strong communicator; able to partner effectively with DS, DE, and product teams.
Curious, experimental thinker who explores new AI patterns.
Independent owner capable of leading complex initiatives from ideation to production.
Customer-first mindset to reduce friction for ML practitioners.

Qualifications

Bachelor’s or Master’s degree in CS, Engineering, AI/ML (mandatory due to vendor requirement).
Strong foundation in ML fundamentals, distributed systems, and cloud-native engineering.
Experience deploying scalable AI/ML solutions in production environments.