Abhinav Bohra
Amazon.com, Inc, Senior Applied Scientist
Seattle, Washington, United States
Actions
I'm a Senior Applied Scientist at Amazon with experience building scalable Agentic systems, Recommender systems, Pricing systems. I lead the development of LLM-based product retrieval and ranking systems at Amazon Advertising.
I also serve as a Co-Chair for ACM RecSys, top tier international conference in recommender systems, senior IEEE author, technical writer at HackerNoon and mentors early stage startup teams on AI/ML strategy.
Area of Expertise
Topics
The Anatomy of DuckDB: How an In-Process OLAP Engine Works in Pure Python
Most Python developers reach for DuckDB because it is fast. This talk explains why it is fast — and what that means for how you should use it. We start at the engine layer: columnar storage, the push-based vectorised execution model, and how DuckDB's query planner differs from row-oriented databases. We then move to the Python integration layer: zero-copy exchange with Arrow and pandas, the relation API versus raw SQL, and how DuckDB manages memory within your process. The second half is benchmarks — DuckDB vs pandas vs PySpark on aggregations, joins, and window functions at 10M, 100M, and 1B rows — with honest commentary on where each tool belongs in a modern data stack. Leave with a mental model, not just a tutorial.
Beyond RAG: Agentic Context Engineering for Reliable Enterprise AI
Most production AI agents fail before reasoning begins: their context is noisy, incomplete, stale, too long, or impossible to verify. This talk shows how to build structured context layers that make agents, RAG systems, search, and recommendation pipelines more reliable in real enterprise environments.
Drawing from billion-scale LLM system experience, we will cover practical patterns for converting messy enterprise data such as documents, logs, tickets, policies, conversations, knowledge bases, catalogs, and multimodal assets into compact, inspectable, continuously evaluated context. The architecture combines schema discovery, self-supervised extraction, teacher-student distillation, context compression, influence scoring, deterministic guardrails, and LLM-as-judge monitoring.
Attendees will leave with a blueprint for building agent ready data infrastructure that reduces cost, improves reliability, supports evolving schemas, and makes AI decisions easier to evaluate and defend.
Agentic Loops in the Data Stack: From Pipeline Failure to Auto-Remediation
Every data engineer knows the 2 AM pipeline failure — the one nobody notices until Friday's report is wrong. In this session, we break down five AI agents that are changing how data teams operate: from monitoring pipelines 24/7 and catching schema drift at ingestion, to closing the gap between a production failure and its root cause in minutes. We'll walk through real implementation patterns, including a baseline-learning monitoring agent and a tool-use driven incident response loop, and discuss what the shift to agentic data engineering actually means for the way teams are built and how engineers grow. Whether you're evaluating agents for your platform or already running them in production, you'll leave with concrete patterns you can apply immediately.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top