Tech stack
Anyone can build an AI proof of concept. The hard part is keeping it running in production. ALBY's strength isn't only building — it's keeping things running.
— Focus
Not just building —
we're strong at keeping things running
As a small, senior engineering studio, we work from first idea to day-to-day operations, centred on running LLMs and generative AI in production, reliability engineering through SRE/DBRE, and Kubernetes and cloud infrastructure. We're especially good at the part most teams are thin on: stable operation and cost control in production.
LLMs and generative AI in production
LLM / GenAI
Not stopping at a proof of concept — running LLM applications reliably in production. From implementation through LLMOps and inference cost optimisation.
Reliability engineering
SRE / DBRE
Observability, automation, and continuous improvement for systems that stay up. Including database reliability (DBRE).
Kubernetes and cloud infrastructure
Kubernetes / Cloud
Designing, operating, and cost-optimising Kubernetes and AWS/GCP. Infrastructure that scales, in a form your team can realistically run.
Robust, type-safe development
Type-safe Dev
Rust, TypeScript, and Scala. We lean on type systems to write code that resists breakage and welcomes change.
— Stack
Technologies we work with
We pick the right technology for the problem at hand. Below are the ones we work with day to day.
Languages
- TypeScript
- Rust
- Scala
- Python
- Go
AI / LLM
- LLM application development
- RAG
- LLMOps
- Prompt design
- Generative AI operations & cost control
Cloud / Infrastructure
Cloud / Infra- Kubernetes
- AWS
- Google Cloud
- Cloudflare
- Terraform
Data & databases
Data- PostgreSQL
- Supabase
- DBRE
- NoSQL
Observability & operations
Observability- Monitoring & alerting design
- CI/CD
- Datadog
- Prometheus
Contact
Let's talk it through.
Questions and estimates are always welcome — no commitment needed.