Senior Software Engineer • AI Systems | Platform Engineering
Designing reliable, scalable AI systems at production scale
🔭 Building AI systems and developer platforms with a focus on reliability and scale
🌱 Exploring LLM inference efficiency, agent safety, and system observability
💬 Ask me about distributed systems, Python/Java, cloud platforms, and AI agents
📫 Reach me at codewithnk@gmail.com
LLMs • Agentic Systems • Execution Feedback Loops • Retrieval
Inference Performance • Cost / Latency Tradeoffs • Safety Constraints
Kubernetes • Serverless • CI/CD • Observability
Private Networking • Fault Tolerance • System Design
ETL Platforms • Lakehouse Architectures • Apache Spark
SQL Engines • Cost Optimization
Python • Java • TypeScript • Spring • Node.js
Concurrency • Distributed Systems
- Determinism before scale
- Observability before optimization
- Clear interfaces enable fast, safe systems
- Prefer boring, reliable systems over clever hacks
✔️ Reduced cloud costs by 30% through architectural and execution optimizations
✔️ Cut onboarding time from months to weeks via platform automation
✔️ Built end-to-end AI and data platforms with strong reliability guarantees
✔️ Focused on correctness, observability, and system clarity