Generative AI Engineer – LLM & Agentic Systems – AIRLHV

Job Summary

NavitasPartners is seeking a Generative AI Engineer – LLM & Agentic Systems to join their remote/hybrid team serving clients across the US and Canada. This contract/full‑time role is based in Red Deer, Red Deer region, Canada.

Key Responsibilities

• Design, develop, and deploy large language model (LLM) powered applications and autonomous AI agents.
• Integrate generative AI solutions with enterprise data platforms, APIs, and knowledge bases.
• Optimize model performance, scalability, and latency for production environments.
• Collaborate with data engineers, product managers, and UX designers to deliver end‑to‑end AI solutions.
• Implement monitoring, logging, and continuous improvement pipelines for AI services.
• Stay current with emerging LLM research, prompting techniques, and agentic frameworks.

Required Qualifications

• Bachelor’s or higher in Computer Science, AI, Machine Learning, or related field.
• 3+ years of hands‑on experience with LLMs (e.g., GPT, Llama, Claude) and prompt engineering.
• Proficiency in Python and AI/ML libraries such as PyTorch, TensorFlow, Hugging Face Transformers.
• Experience building AI agents, tool‑use pipelines, or autonomous workflows.
• Strong understanding of cloud platforms (AWS, Azure, GCP) and container orchestration (Docker, Kubernetes).
• Ability to work independently in a remote/hybrid setting and communicate technical concepts clearly.

Preferred Skills

• Experience with Retrieval‑Augmented Generation (RAG) and knowledge‑graph integration.
• Familiarity with MLOps tools (MLflow, Kubeflow, CI/CD pipelines).
• Background in enterprise security, compliance, and data governance for AI.

What We Offer

• Competitive contract rates with flexible work arrangements.
• Opportunity to shape cutting‑edge generative AI products for enterprise clients.
• Collaborative, innovation‑focused team environment.

Frequently Asked Questions

Is this position remote or on‑site?

The role is remote/hybrid, allowing you to work from Red Deer or any location in the US/Canada with occasional on‑site collaboration.

What level of experience is required?

At least three years of professional experience with large language models, prompt engineering, and AI agent development.

Do I need a specific cloud certification?

A formal certification is not required, but solid experience with AWS, Azure, or GCP and container orchestration is essential.