Python Developer

Lorven Technologies Inc.; Mississauga; On-site; CAD 120,000 - 180,000; Full time

Job summary

Lorven Technologies Inc. is seeking a senior GenAI/LLM engineer who will architect and deploy GenAI-powered solutions, focusing on RAG and enterprise integration. You will build end-to-end pipelines, curate prompts, and lead MLOps to production readiness.

The role requires deep knowledge of Python ML ecosystems, vector databases, and orchestration tools, with hands-on work on large language models and enterprise APIs.

Qualifications

• Strong foundations in GenAI, ML, NLP, LLMs, and AI fundamentals.
• Experience with retrieval-augmented generation (RAG) pipelines and production deployments.
• Proficiency in Python and ML libraries and frameworks.
• Experience integrating genAI with enterprise apps and APIs.
• Hands-on with vector databases and data-heavy processing.

Responsibilities

• Design, implement, and deploy GenAI-powered applications and pipelines.
• Develop robust prompt strategies, tuning, and reusable templates.
• Lead MLOps practices, model evaluation, and CI/CD pipelines.
• Collaborate with teams to integrate GenAI features into enterprise systems.

Job description

• 8-10 years of relevant experience in Apps Development or systems analysis role
• Core AI/ML Foundations:
• Strong foundational knowledge in GenAI , Machine Learning (ML modeling), Data Science, Statistics, and AI fundamentals, including Natural Language Processing (NLP), Neural Networks, and Large Language Models (LLMs).
• Generative AI & LLM Expertise:
• Extensive hands-on experience with leading LLMs such as Google Gemini, OpenAI models, Anthropic Claude, Mistral, Llama, and various other open-source LLMs.
• Critical: Deep working knowledge and hands-on experience with Retrieval-Augmented Generation (RAG) pipelines, including advanced RAG techniques and their detailed implementation.
• Proven ability to build, tune, and deploy LLM-based applications using platforms like Vertex AI, Hugging Face, etc.
• Expertise in developing robust prompt engineering strategies, prompt tuning, and creating reusable prompt templates.
• Hands-on experience with agentic framework-based use case implementation.
• Working knowledge of Guardrails and methodologies for assessing the performance and safety of GenAI features.
• Strong programming proficiency in Python is a must, including extensive experience with libraries such as Pandas, NumPy, scikit-learn, PyTorch, TensorFlow, Transformers, FastAPI, Seaborn, LangChain, and LlamaIndex.
• Proficiency in integrating generative AI with enterprise applications using APIs, knowledge graphs, and orchestration tools.
• Hands-on experience with various vector databases (e.g., PG Vector, Pinecone, Mongo Atlas, Neo4j) for efficient data storage and retrieval.
• Experience in dealing with large amounts of unstructured data and designing solutions for high-throughput processing.
• Deployment & MLOps:
• Critical: Hands-on experience deploying GenAI-based models to production environments.
• Strong understanding and practical experience with MLOps principles, model evaluation, and establishing robust deployment pipelines.
• Strong expertise in CI/CD principles and tools (e.g., Jenkins, GitLab CI, Azure DevOps, ArgoCD) for automated builds, testing, and deployments.
• Proven experience with container orchestration platforms like OpenShift or Kubernetes for deploying, managing, and scaling containerized applications in a cloud-native environment.