AI Systems Engineer | Automation Architect | Scalable Backend Specialist
I build intelligent, production-grade systems that automate workflows, scale reliably, and stay debuggable over time. My work sits at the intersection of AI agents, backend architecture, full-stack engineering, and applied machine learning. I focus on real-world impact, not just demos.
Agent & LLM Tooling
LangGraph, LangChain, tool-calling agents, memory & planning loops
Retrieval & Search
FAISS-style vector search, embedding pipelines, RAG / CAG / KAG
LLM Ops
Prompt versioning, evaluation, cost & latency tracking
- Frameworks: scikit-learn, TensorFlow, PyTorch
- Models: NLP, CV, tabular, transformers (GPT, BERT)
- Techniques: Fine-tuning, prompt engineering, RAG/CAG/KAG
- Vector Pipelines: FAISS-style embedding search
- Multi-agent architectures
- Tool-calling agents & workflow orchestration
- Autonomous loops (memory, planning, retrieval)
- Reliability-first design (timeouts, retries, fallbacks)
- Stateless/stateful services
- Caching (Redis), async processing, queues
- API design, sharding, infra-aware backends
- Production-grade AI agents
- AI infrastructure and evaluation pipelines
- Automation for real business workflows
- Backend systems that scale without becoming fragile
- Freelance/Contract: AI systems, automation pipelines, backend architecture
- Advisory: Scaling AI-first products
- Open-Source: Agents, RAG tooling, AI infrastructure