Machine Learning into Production podcast, interview style
Episodes
7 Apr 2026
Recommended: An optimistic view of using Agentic AI with safeguards.
AI agents streamline software development through tools like pixel diff analysis, automated reporting, and annotated walkthroughs, addressing challenges in accuracy, code quality, and workflow adaptation while redefining human roles as validation overseers and collaborators in autonomous systems.
Open episode
3 Apr 2026
Optimizing ML workflows requires addressing data bottlenecks through caching, efficient structuring, and hardware-aware strategies to reduce remote data calls, minimize GPU-CPU overhead, and prioritize infrastructure over model tuning, while managing trade-offs between training efficiency and serving latency.
Open episode
31 Mar 2026
Processing live stream data involves transcription, AI-driven skill categorization, GitHub organization, multimedia-comment correlation, and knowledge graphs, while addressing redundancy, AI costs, and MLOps trends, AI agent debates, adversarial workflows, security risks, and tooling like Open Claw and Agent Zero.
Open episode
30 Mar 2026
Deploying AI agents in real-world systems demands robust safety protocols, human oversight, and structured testing to address risks like errors and vulnerabilities, while balancing innovation with responsibility through observability, governance, domain expertise, and tools like MLflow, across use cases from workflow automation to critical system reliability.
Open episode
27 Mar 2026
Epiplexity introduces a framework redefining entropy and complexity with structural information, while topological search and graph-based methods enhance semantic accuracy in machine learning by preserving data through high-dimensional embeddings and hybrid geometric-topological analysis, outperforming traditional approaches in retrieval and reasoning tasks.
Open episode
20 Mar 2026
AI-driven agent systems in OLX's classifieds marketplace aim to innovate user experiences by overcoming UI constraints through dynamic intent extraction, hybrid chat/UI models, and trust-building in real estate and motors, with future focus on logistics automation, secure transactions, and human-agent integration.
Open episode
17 Mar 2026
Temporal enhances developer productivity by enabling crash-proof workflows through deterministic programming models, separating business logic from fault tolerance, and simplifying distributed systems with durable execution, workflows, activities, and persistence layers like Cassandra/Postgres.
Open episode
24 Feb 2026
The podcast dives into AI development, software engineering, and GPU innovation, focusing on efficient workloads and the trade-offs between quick solutions and scalable systems.
Open episode
19 Feb 2026
AI model deployment requires careful planning of infrastructure and scalability to ensure smooth transition from experimental to production stages, considering factors like cost, performance, and control.
Open episode
13 Feb 2026
The podcast highlights the importance of context, flexibility, and evolution in workflow tools and data analysis, emphasizing the need for refinement and dynamic interaction with AI agents.
Open episode