BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//aiweek.boston//Schedule//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:PyData Boston AI talks
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pydata-boston-ai-talks@aiweek.boston
DTSTAMP:20260912T005915Z
SEQUENCE:0
STATUS:CONFIRMED
DTSTART;TZID=America/New_York:20260930T183000
DTEND;TZID=America/New_York:20260930T213000
SUMMARY:PyData Boston AI talks
DESCRIPTION:Join the Boston PyData community as we talk about topics rela
 ted to AI with an emphasis on open source technology!\n\nWe'll start with
  an intro to building agents in multiple frameworks\, move on to consider
 ations around hosting LLMs and wrap up with a dive into responsible AI. J
 oin us!\n\nDo not arrive before 6:30pm!\n📅 Schedule:\n6:30–7:00 — Networ
 king (doors open)\n7:00–7:10 — Introduction\n7:10–7:35 — Krithika Muruges
 an - Building Agentic AI Systems\n7:35-8:00 - Sebastian Wallkötter - The 
 physics behind (self-)hosting LLMs\n8:00–8:30 - Break\n8:30-8:55 — Ananya
  Sharma - Detecting and Mitigating Bias in Automated Mortgage Lending\n9:
 30 — End\n\n**IMPORTANT** You MUST register here in order to attend: http
 s://www.meetup.com/pydata-boston-cambridge/events/316514602\n\nKrithika M
 urugesan\nTitle: Building Agentic AI Systems\nDescription: In this sessio
 n\, I will introduce the fundamentals of Agentic AI and demonstrate how t
 o build intelligent\, autonomous AI systems using modern frameworks such 
 as LangGraph\, LangSmith\, and CrewAI. Participants will learn how AI age
 nts reason\, collaborate\, use tools\, maintain state\, and execute compl
 ex workflows through practical examples and architecture patterns.\n\nSeb
 astian Wallkötter\nTitle: The physics behind (self-)hosting LLMs\nDescrip
 tion: Why do output tokens cost more than input tokens? Why are batch API
  calls 50% cheaper than normal API calls? Where does the $/M token price 
 come from in the first place? I want to answer this while building a cost
  model for a local LLM deployment. We'll cover compute\, bandwidth\, and 
 vRAM dynamics and the effects of K/V cache\, context window\, quantizatio
 n\, GQA (grouped-query attention)\, and multi-request batching. Think of 
 this as a (high-level) behind-the-scenes of a per-token LLM API.\n\nAnany
 a Sharma\nTitle: Detecting and Mitigating Bias in Automated Mortgage Lend
 ing\nDescription: How can an AI system discriminate without ever seeing p
 rotected attributes? This talk explores how automated mortgage models can
  reproduce historical lending disparities through proxy variables and bia
 sed data. It presents practical approaches for detecting and mitigating a
 lgorithmic bias using statistical fairness testing\, explainability\, mod
 el governance\, and continuous monitoring (edited)
LOCATION:Kendall Square in Kendall - see the meetup link for details: htt
 ps://www.meetup.com/pydata-boston-cambridge/events/316514602\, See the me
 etup link for details: https://www.meetup.com/pydata-boston-cambridge/eve
 nts/316514602
URL:https://aiweek.boston/schedule/pydata-boston-ai-talks
BEGIN:VALARM
ACTION:DISPLAY
DESCRIPTION:PyData Boston AI talks
TRIGGER:-P1D
END:VALARM
BEGIN:VALARM
ACTION:DISPLAY
DESCRIPTION:PyData Boston AI talks
TRIGGER:-PT1H
END:VALARM
END:VEVENT
END:VCALENDAR