Senior Software Engineer
Kodesage · Kodesage HU · Posted Apr 21, 2026
Transparency
DeadOnline for 30 weeks and never reposted. Jobs this old or reposted this often rarely lead to a hire. It may be filled already.
- First seen
- Oct 10, 2026
- Offered for
- 213 days
Overview
- Category
- Software engineering
- Employment type
- Permanent
- Workplace type
- On-site
- Country
- Hungary
- Seniority
- Senior
- Schedule
- Full time
- Salary
- Not listed
Key skills
- Microservices Production Services
- Design, build, and operate scalable services in a distributed microservices environment.
- LLM Feature Development
- Create and ship LLM‑based features such as prompts, evaluation, streaming, and cost/latency trade‑offs.
- Software Engineering Fundamentals
- Write clean, readable, extensible code using modern backend or frontend languages and frameworks.
- Production Tooling
- Utilize Docker, CI/CD pipelines, monitoring, and deployment processes for reliable service delivery.
- AI‑Assisted Development Workflows
- Integrate coding assistants and prompt engineering to amplify development productivity.
Key phrases
- distributed, microservices setup
- Ship LLM features
- prompts, evaluation, streaming
- clean architecture
- readable and extensible code
- Python, Rust, Go, Java, Angular, React
- Docker, CI/CD, monitoring and deployments
- coding assistants (Claude Code, Codex, Antigravity, Cursor
- read technical papers
- prompt engineering
- model evaluation
From the posting
About Kodesage
Kodesage helps enterprises understand, operate and modernize their legacy systems. We’re a growing team building an AI-augmented developer platform.
At Kodesage, you decide how you solve problems, in a seasoned team. We look for people who take ownership and believe the best idea wins, whoever it comes from. If that sounds like you, we’d love to hear from you.
Why this role exists
Engineers who inherit legacy code spend more time deciphering it than improving it. You’ll build the LLM-powered solution that helps them understand and modernize it.
What you'll do
Build and run production services in a distributed, microservices setup
Ship LLM features: prompts, evaluation, streaming, and cost and latency trade-offs
Own features end to end, from backend to frontend
Shape how things are built in a growing team, where priorities evolve and you’ll get to work across different areas
What you bring
Strong software engineering fundamentals - clean architecture, readable and extensible code - in any modern backend or frontend language or framework (Python, Rust, Go, Java, Angular, React or similar). We’re language-agnostic, and strong engineers from any background are welcome
Familiarity with building and running software in production - for example Docker, CI/CD, monitoring and deployments - ideally in a microservices or distributed systems context
Experience with AI-assisted development workflows - using coding assistants (Claude Code, Codex, Antigravity, Cursor or similar) as a daily multiplier, and an opinion on how to get the most out of them
Ability to read technical papers and turn the findings into working code
Strong written and verbal communication skills in English
Nice to have
Practical experience with LLMs in production - prompt engineering, model evaluation, streaming, cost/latency trade-offs
Vector search, embeddings and semantic retrieval
Code parsing, static analysis or compiler tooling
Legacy codebases, enterprise modernization, or on-premise / self-hosted B2B products
Agentic engineering - building or extending AI agents, tool use, multi-step reasoning systems
Startup experience
How we work
Ownership: you take a feature from idea to production and stay responsible for it
Pragmatism: you ship the simplest thing that solves the problem
Curiosity: you keep up with AI and bring ideas to the team
Craft: your code is typed, tested and reviewable
Collaboration: you communicate clearly and give direct feedback
The industry left legacy systems behind, but we didn't. Join a team decoding complex systems that even the best AI models can't crack on their own.
