We are seeking an ML and MLOps Engineer with expertise in AI debugging, Retrieval-Augmented Generation (RAG) applications, and designing agentic behaviors in AI systems. The role involves creating scalable ML pipelines, building intelligent RAG solutions, enabling agentic behaviors in AI workflows, and developing reusable components for low-code/no-code platforms.
Key Responsibilities:
Develop and maintain RAG workflows integrating LLMs with external knowledge bases for enhanced context retrieval.
Debug AI models by identifying and resolving issues in performance, behavior, and reliability.
Design and deploy scalable ML pipelines using CI/CD and MLOps tools.
Implement agentic behaviors in AI systems to support autonomous decision-making and task completion.
Create and maintain templates and reusable components to facilitate low-code/no-code solutions for deploying AI models.
Implement observability frameworks for monitoring and troubleshooting AI systems in production.
Manage data pipelines, preprocess data for RAG models, and optimize vector search using embeddings.
Collaborate with cross-functional teams to integrate RAG solutions, agentic workflows, and templates into production environments.
Continuously evaluate and optimize model performance using AI debugging tools and techniques.
Skills and Qualifications:
Proficiency in Python and ML frameworks (e.g., PyTorch, Hugging Face Transformers).
Strong understanding of RAG principles, vector search engines (e.g., Pinecone, FAISS, Weaviate), and LLM architectures.
Experience in designing agentic behaviors in AI systems to enable autonomous and context-aware interactions.
Expertise in debugging AI systems, identifying performance bottlenecks, and resolving errors.
Hands-on experience with MLOps tools (e.g., MLflow, Kubeflow) and cloud platforms (AWS, GCP, Azure).
Familiarity with REST APIs, containerization (Docker), and orchestration (Kubernetes).
Knowledge of observability tools for tracking model behavior in production.
Ability to design reusable components and workflows for low-code/no-code AI integration.
Skills Required:
Experience in fine-tuning LLMs for RAG workflows and embedding generation.
Familiarity with distributed training and scaling AI models for production environments.
Knowledge of techniques for optimizing retrieval systems, such as hybrid search or prompt engineering.
Understanding of goal-driven agentic systems, multi-agent frameworks, synthetic dataset generation and Evaluation techniques.
Conditions:
We are looking to get Co-founders who will work with the team as a partner. This is equity based, please know this before applying.
