Krishna Gove

Krishna Gove

I build AI and ML systems at Audi in Munich, on top of fourteen years spent running the infrastructure underneath them. Before this: DevOps and SRE at IABG, Infineon, Wipro and Thomson Reuters, and a long stretch of Linux administration before that.

Fourteen years, six companies, and the code below ↓

About

Most of my career has been on the operations side: Linux across a few hundred nodes, CI/CD pipelines, Kubernetes, and the pager. The last few years I have been building AI systems instead, and the two turn out to be the same job. A RAG pipeline that works in a notebook and a service that survives a Tuesday afternoon are very different pieces of software.

So what I am useful for is the part after the demo. Where does this break, what does it cost, how will we know when it goes wrong, and what happens at 3am. At Audi that currently means AWS infrastructure, MLOps pipelines, and LLM automation that people other than me depend on.

I studied Business Analytics and Data Science at EU Business School in Munich alongside the work, and I was a top finalist in the AWS Agentic AI Hackathon.

Experience

Audi AG, Munich

02/2026 to now
Software Engineer
  • Cloud infrastructure on AWS with CDK, EKS and Docker. Containerised over 10 microservices and cut deployment cycles by 45%.
  • AI and ML pipelines behind Python REST APIs in FastAPI and Pydantic, used by 5 product teams. ML throughput up 35%.
  • LLM automation, RAG and agentic workflows with LangChain, which cut experimentation time by around 60%.
  • Observability with Prometheus, Grafana and Datadog, and 28% off API response times through async refactoring.

IABG, Munich

12/2024 to 12/2025
Software Engineer
  • Over 8 REST APIs and real-time data pipelines for autonomous defence systems. Mission planning cycle time down 40%.
  • Tools and dashboards for 3 safety-critical robotics applications, and 30% off distributed system latency.

Infineon Technologies, Munich

02/2024 to 10/2024
DevOps Engineer
  • Rebuilt CI/CD across 4 environments with Jenkins and ArgoCD. Deployment frequency up 60% through parallel test execution.
  • Prometheus, Grafana and ELK across 12 services, which removed 4 hours of downtime a month through early alerting.

Wipro, Hyderabad

11/2021 to 10/2023
DevOps Engineer
  • Kubernetes across 3 cloud environments, infrastructure in Terraform and Ansible, 20 Docker images packaged.
  • Deployment failures down 35%, and 60% of manual ops work automated away in Python and Bash.

Thomson Reuters, Bengaluru

01/2019 to 10/2021
DevOps Engineer
  • CI/CD for over 50 deployments a day at 99.99% uptime, on SLO-driven monitoring and structured incident response.
  • Build times down 30% by parallelising test stages.

IBM, Hyderabad

01/2016 to 06/2018
Linux Administrator
  • Red Hat, Ubuntu and CentOS across 200 nodes. Hardening, performance tuning, and a lot of Bash.

Earlier: System Engineer at Tech Mahindra (2014 to 2015), Desktop Engineer at Zensar Technologies (2011 to 2013).

Things I have built

Side projects, all public. Each one runs with a single command, ships a test suite that runs in CI, and shows real output in its README. The READMEs also say where each design stops working, because that is usually the more useful half.

realtime-ad-delivery

Ad decisioning inside a latency budget: targeting, pacing, frequency caps, budget. Answers in about a millisecond, and the README measures the point where that stops being true.

Node.js · TypeScript · PostgreSQL · Docker · 93 tests

oauth2-token-service

An OAuth2 server: PKCE, refresh token rotation with reuse detection, RS256 with a published JWKS. Every security rule has a test that carries out the attack it stops.

Node.js · TypeScript · PostgreSQL · 144 tests

feature-flags

Feature flags with sticky percentage rollouts and attribute targeting, plus a React admin UI. Bucketing hashes the flag key with the user, so one unlucky user does not land in every experiment at once.

Node.js · TypeScript · React · PostgreSQL · 85 tests

agent-trajectory-eval

Scores an LLM agent on how it behaved, not just what it answered: tool choice, forbidden tools, redundant steps, budget.

Python · Agent evaluation

slo-error-budget

Error budget, burn rate, and multi-window paging from the Google SRE workbook. Answers whether to wake someone, rather than what the availability number is.

Python · SRE

kubernetes-resource-rightsizer

Right-sizes CPU and memory requests from real usage, and flags throttling and OOM risk before they find you.

Python · Kubernetes

The rest are on GitHub, including LLM observability, semantic caching, RAG, and prompt-injection work.

One of them running

slo-error-budget, because it is the shortest thing to read. "We are at 99.9% availability" does not tell you whether to wake anyone up.

$ make demo
30-day error budget:
{
  "slo": 0.999,
  "sli": 0.9995,
  "budget_consumed": 0.5,
  "budget_remaining": 0.5,
  "burn_rate": 0.5,
  "hours_to_exhaustion": 720.0,
  "healthy": true
}

spike burn rates  short=30.0x  long=15.0x  ->  alert: page

Half the budget is gone, so at this rate it lasts another 720 hours. Then a spike burns 30x over five minutes and 15x over the hour. Both windows are hot, so it pages. A five second blip would not, which is the entire point.

Certifications and study

Get in touch

If you are working on production AI, platform engineering, or the unglamorous infrastructure that holds either of them up, I am happy to talk. The fastest way to reach me is krishnagove88@gmail.com, and I am on LinkedIn.