Distributed Systems, Python, latency optimization, system observability, production infrastructure, cost efficiency, deployment pipelines

Elk, Prometheus, Bash, Grafana, Python, Kubernetes, Linux environments, NVIDIA BCM, Slurm

Python, RAG systems, CI/CD pipelines, agentic AI systems, DevOps practices for AI, LLM orchestration, vector databases, AI frameworks, prompt engineering, cross-platform development

Arp, Tcpdump, routing, Wireshark, BGP, Vlans, Iperf, QoS policy, routing tables, latency, packet loss, eBGP, route policy, MTU, iBGP, RoCEv2, interoperability testing, switch qualification, RDMA fabric designs, L3 routing, ECMP, multipath BGP-based fabrics, Linux networking interfaces, congestion, L3 data center networks, ND, performance characterization, namespaces

Java, Algorithms, C++, Networking, Operating Systems, Data structures, Python, Microservices, Go, Distributed System Design, Service governance

Apis, Debugging, Data Structures, Kafka, Redis, Algorithms, Docker, Testing, Kubernetes, Python, Cloud-native Systems, Prompting, Agent Workflows, RAG Tool Calling, LLM Evaluation, Agent Systems, LLM Applications, Function Calling, Asynchronous Services

Kubernetes, AI observability tooling, GPU infrastructure management