14 Nov
|
Pulse craft Technologies
|
Winnipeg
14 Nov
Pulse craft Technologies
Winnipeg
Oshawa, ON (Hybrid / Remote) 4+ Years Experience Posted 2026-08-20 Role Overview
Lead the architecture and implementation of cutting-edge generative AI, enterprise RAG systems, autonomous agent workflows, and fine-tuned foundational models for our global client portfolio. Core Responsibilities
Design and deploy scalable RAG pipelines using LangChain, LlamaIndex, and vector databases (Pinecone, pgvector) Evaluate, fine-tune, and optimize open-source and proprietary LLMs for domain-specific tasks Implement robust evaluation frameworks, guardrails, and latency optimization for real-time AI responses Collaborate with enterprise clients to translate unstructured data challenges into high-value AI solutions Qualifications & Requirements
Deep understanding of transformer architectures, attention mechanisms, and embedding spaces Proficiency with Python, PyTorch, FastAPI, and modern AI SDKs (OpenAI, Anthropic, HuggingFace) Hands-on experience deploying vector search and semantic retrieval pipelines at enterprise scale Robust background in data privacy, zero-leakage enterprise security, and prompt safety Executive equity package Full health & dental GPU cloud compute allowance Global conferences
📌 AI & LLM Solutions Architect (Winnipeg)
🏢 Pulse craft Technologies
📍 Winnipeg