An operations colleague was about to demo in front of 50 people and a feature broke. It was diagnosed, fixed and deployed in 15 minutes, before the demo started. We shall not focus on whose fault it was , but "what do we change so it can't recur." Solve the problem, not blame the people.
Every piece of work lives in Cadence, our own internal platform , built in-house, used daily. If something's broken, it becomes a ticket everyone can see, not a message that dies in someone's excel, whatsapp , notebook etc. No ticket means no work.
The best PR we merged recently wasn't the fastest one. It came with integration tests and a UX thought through so carefully that our operations team could teach it to a client without a manual. That's the bar: build for the person who receives your work, not the person who does it.
...
Experience: 4+ years in software development, with 2+ years of production Rust (or exceptional Rust proficiency with strong systems/backend background); enterprise or fintech/e-invoicing domain experience preferred.
Programming Skills: Proficient in Rust (async/await, traits, feature-gated compilation targets); working knowledge of SQL, HTML, CSS, TypeScript (for e2e tooling).
Full-Stack Rust: Hands-on experience with a Rust web framework (Leptos, Axum, Actix, Yew, or Dioxus) and WASM compilation; understanding of SSR + hydration trade-offs.
...
We are looking for an exceptional Senior/Staff Full Stack Engineer with 10+ years of engineering experience to build the next generation of AI-native software systems.
This is not a traditional full-stack role. We are looking for someone who understands how to build systems where AI agents can reason, execute, observe outcomes, learn from feedback, and continuously improve their own performance.
...
We are looking for an exceptional Senior/Staff Full Stack Engineer with 10+ years of engineering experience to build the next generation of AI-native software systems.
This is not a traditional full-stack role. We are looking for someone who understands how to build systems where AI agents can reason, execute, observe outcomes, learn from feedback, and continuously improve their own performance.
...
Agentic AI ArchitectureDesign and implement production-grade agentic systems using models such as Claude. Agent orchestration, tool calling, function calling, multi-agent architectures, planning and task decomposition, agent memory, context management, state machines and workflow engines, long-running agents, human-in-the-loop systems, autonomous execution, recovery and retry mechanisms, observability, and evaluation. You understand the difference between LLM → Agent → Workflow → Autonomous System, and when each is appropriate.
Agentic Loops & Self-OptimizationA major part of the role is building closed-loop systems: Goal → Plan → Execute → Observe → Evaluate → Learn → Re-plan → Execute. Systems that evaluate their own outputs, detect failed actions, identify root causes, adjust strategies, optimize prompts and tool selection, keep what works, roll back what does not, and improve over time. Reflection, critique, self-evaluation, feedback loops, reward signals, evaluation frameworks, automated experimentation, memory, retrieval, state management.
Claude / LLM EngineeringDeep practical experience with Claude/Anthropic APIs is highly desirable. Tool use, structured outputs, streaming, context management, prompt engineering, system prompts, long-context workflows, model routing, token optimization, latency and cost optimization, context compression, agent memory, LLM evaluation. Experience with other frontier models (OpenAI, Gemini, Llama or equivalent) is a plus.
...
Assuming the role of a technical expert for solution design and development with the responsibilities below:
Partner with business stakeholders, product owners and project managers to understand business requirements and translate them into technical design.
...