Curriculum Vitae

Peleke Sengstacke

Research engineer building instrumented agent platforms and studying how they learn, how faithfully they reason, and what it takes to monitor them in production.

Atlanta, GA peleke@peleke.me github.com/peleke linkedin.com/in/peleke

Research

Can agents learn to optimize their own context?

Instrumented agent architecture for measuring whether agents can learn to optimize their own context. Beta-Bernoulli Thompson Sampling over context components, experimental causal knowledge graph, end-to-end observability via OpenTelemetry. Open-source and functional.

View the full research program →

Experience

Independent Research & Engineering

October 2024 – Present

  • Building Vindler/qlawbox: instrumented agent runtime with Bayesian learning, causal knowledge graph, and post-deployment observability
  • Overclock Accelerator (Sep 2025 – Jan 2026): SME for practitioner-facing agentic engineering curriculum
  • Shipped Interlinear, LinWheel, and Swae OS as experimental surfaces for operationalizing research at the product interface

Principal Engineer

$60MM+ ARR · 60+ NPS

edX / 2U

March 2021 – September 2024

  • Architected distributed sandbox platform for Cybersecurity Bootcamp serving 40+ universities internationally
  • Built golden VM images (Ansible + Packer) with CI-managed rebuilds into Azure VM registries
  • 10x provisioning performance via async-first migration; 66% cloud compute cost reduction through lifecycle management

Lead Architect, Cybersecurity

acq. $750M

Trilogy / 2U

March 2019 – March 2021

  • Created dedicated engineering function; hired, trained, and managed 3 engineers
  • Shipped sandbox platform serving 40+ universities; revenue grew to $60MM+ ARR
  • Early experiments in Dockerized lab environments for secure, distributable sandboxed execution

Lead Curriculum Architect

Trilogy / 2U

October 2018 – March 2019

  • Owned, built, and shipped 24-week Cybersecurity Bootcamp (Trilogy's 4th product line)
  • Co-instructed first cohort at Georgia Tech

Lead Curriculum Engineer

Trilogy

July 2016 – October 2018

  • First full-time curriculum engineer hired to build content; ended up building programs
  • Authored coursework: Django, Laravel, MERN, testing, data visualization, ML
  • Top-rated instructor at Rutgers (Full Stack) and Georgia Tech (Cybersecurity)

Surfaces

Interlinear

Adaptive learning platform

Course generation from arbitrary text sequences with morphosyntactic error classification feeding Thompson Sampling. CLTK + Reynir NLP pipelines for Classical Latin and Icelandic.

CLTK · Reynir · Mastra · Next.js 15 · Supabase

Swae OS

Federated multi-service health platform

Expo frontend, Hive Gateway federation, Tofu-managed Cloud Run mesh with isolated Supabase schemas. Hub-and-spoke reference architecture for multi-domain applications.

Expo · GraphQL Federation · Hive Gateway · OpenTofu · FastAPI · Cloud Run

LinWheel

Agent-to-external-surface publishing layer

Principled channels for agent access to external publication surfaces with bounded output space. PyDoll browser automation for LinkedIn's missing article API.

PyDoll · HMAC Signing · FAL Flux.1 · Claude · Next.js

ComfyUI MCP

Neural network model interface

35+ MCP tools over a general interface to arbitrary models via ComfyUI. Distributed GPU across Fly.io and RunPod. 467 tests.

MCP SDK · Distributed GPU · ComfyUI · Fly.io · RunPod

Education

Princeton University

Computer Science

AWS Certified Solutions Architect – Associate

2023–2026

← About
Book a call Lab →