Curriculum vitae

Ines Panker, senior staff software engineer and conference speaker. 16 years in software, the last 6 as the first engineer and de-facto architect of a SaaS observability platform. The engineering teams built on what I designed, and I led the response when complex incidents crossed system boundaries.

Lately my work has turned toward LLMs: I’ve worked on the LLM pipeline for our AI-usage analytics tool (a tool that gives insights into what your team does with AI). I’ve shipped my first RAG, written many Claude skills and rules and have built several agents for my own tooling.

I also love speaking at conferences, like Devoxx Belgium (3,000+ developers, sells out in minutes), J-Fall (the biggest Java conference in the Netherlands) and Python Italia. Some talks come straight from the systems above: what happens when a third-party API goes down, and how to tell if a deploy broke production. The others are about the lies we tell ourselves: how we estimate, how we argue, …

Based in
Ljubljana, Slovenia (EU citizen)
Working
Remote since 2017, mostly with US teams
Languages
Slovenian (native)
English (fluent)
German (fluent)
French (basic)

What I work with

Core

Python Go Django Flask Celery PostgreSQL Redis RabbitMQ Elasticsearch

Systems

Multi-tenant SaaS Circuit breakers Distributed locking

Data

Pandas Anomaly detection Time series

LLMs

LLM agents Context engineering RAG

Explaining

Technical writing Documentation Teaching Conference talks

Earlier

PHP MySQL JavaScript C# Java

Experience

2020 – now

Senior Staff Software Engineer, Sleuth (San Francisco, remote)

The first engineer they hired, and the de-facto architect ever since. Sleuth is a multi-tenant SaaS observability platform for DORA metrics, environment health and real-time anomalies, fed by 30+ third-party services. I joined when it was two coding founders and a small codebase; the company grew to about 40 people, with the engineering teams building on that architecture.

  • Architecture: set the technical direction the engineering teams built on. Designed the multi-tenant data model, tenant isolation, service boundaries and API contracts, and built the integration framework behind webhook and API ingestion from 30+ third-party services (Datadog, Sentry, PagerDuty, GitHub...).
  • Resilience: designed a circuit breaker system guarding, at peak, 2-3 million API calls a day, added PostgreSQL advisory locks and Redis distributed locks for cluster-wide concurrency, and made Celery tasks transaction-aware to prevent race conditions.
  • Background jobs: set up and maintained the Celery workers that run all of Sleuth's background work, with separate queues for each kind of work. Led the reliability project when jobs kept failing halfway and customer data went missing: planned the milestones, split the work across the team, and moved us from Redis to RabbitMQ.
  • The MTTR engine: built the engine that attributes deploys to incident episodes, which is where the platform's mean-time-to-recovery number comes from.
  • Applied ML: created a self-tuning anomaly detector for customer metrics, with a fresh data point every 2 minutes, running for hundreds of clients for years without hand-tuning. How it works, explained with pictures.
  • LLM work: worked on the pipeline behind Sleuth's AI-usage analytics, and built the small RAG behind the product's AI assistant.
  • Go tooling: built sx, an open-source CLI (300+ GitHub stars) that gives a whole team the same AI skills and rules in whichever coding tool each person uses: Copilot, Codex, Gemini, Cline, Kiro, including team scoping and role-based access.

Python Go Django Celery PostgreSQL Redis RabbitMQ Elasticsearch Pandas

2017 – 2019

Software Engineer, Reciprocity (now ZenGRC, San Francisco, remote)

  • Reverse-engineered the legacy query patterns, mapped the hidden dependencies, and rebuilt the model layer on top of what I found.
  • Ran internal training sessions on development environments, performance work and code practices.

Python Flask SQLAlchemy PostgreSQL

2011 – 2017

Software Engineer, Innovatif (Ljubljana)

  • Led the build of a full e-commerce platform.
  • Built custom web applications for clients, and ran the deployment lifecycle on the Linux servers they lived on.

PHP MySQL JavaScript jQuery

2010 – 2011

Software Engineer, Infonova (Ljubljana)

First full-time job: an automated monthly invoicing system, from the calculation logic to the rendered documents.

C# Java JavaScript

2006 – 2007

Lecturer (student job), Housing Co. (Ljubljana)

Taught adults the basics of computers and Microsoft Office. The explaining-things career started before the engineering one.

On the side

2026 – now

Agents that do real work for me

Confetti, my own conference tracker: two Claude agents research conferences and return structured JSON, deterministic Python validates it and writes the data. Each agent gets two tools and a four-sentence brief and nothing else: no project context, no MCP servers, none of the coding-agent scaffolding. Every run carries a hard dollar ceiling and logs what it cost.

2019 – now

Writing this blog

Either production problems I had to solve, written up with diagrams: rate limits, circuit breakers, spotting a bad deploy. Or observations about humans interacting with code: cognitive biases that make smart devs write silly code, how we lie to each other with stats, ...

2017 – now

One product, all of it

My partner's business site, where I am the entire team: the full-stack engineer, the designer, the sysadmin, and even the marketing.

2006 – now

Teaching, and later conference speaking

I started teaching before I learned programming. Lately, I speak at big developer conferences like Devoxx Belgium (3,000+ developers, sells out in minutes), J-Fall (the biggest Java conference in the Netherlands) and PyCon Italia, all in my own time, no sponsors and no employer agenda. Some talks come straight from the systems above: what happens when a third-party API goes down, and how to tell if a deploy broke production. The others are about the lies we tell ourselves: how we estimate, how we argue, ... The full record and the talk catalogue.

Education

2012

B.Sc. Computer Science, University of Ljubljana

With a semester in 2008 at the University of Southern Denmark, in Odense, on exchange.

next

What I'm looking for

Helping teams make sense of complex systems: a staff engineering role, architecture work, untangling a codebase that's outgrown its team, or developer-facing work where explaining clearly is the job.
Reach me on LinkedIn.