Building the agents that shape what comes next.
I’m a Senior Agentic AI Engineer working on production LLM systems — multi-agent orchestration, hybrid retrieval, MCP-based tool ecosystems, and the eval/observability glue that makes them safe to ship. M.Sc. in Computer Science (AI), first-ranked in cohort. Published in IEEE Access and Neural Computing & Applications. Open to collaborations and senior IC roles.
Claude CLI ↔ OpenAI Proxy
FastAPI proxy that translates OpenAI-format requests to a local Claude CLI subprocess. Tool-call reconstruction, JSON-schema augmentation of system prompts, structured 429/504 error handling, full test suite. Lets any OpenAI-SDK tool target Claude without cloud keys.
FastAPI · async Python · tool-use · OpenAI SDK
Hybrid Agentic RAG — semantic + BM25
Hybrid retrieval combining dense embeddings, BM25 lexical, and reranking inside an agentic loop — the pattern behind production RAG that doesn’t fall over on rare terminology.
hybrid retrieval · rerankers · LangChain
InkFlow · MIT
Real-time capture and analytics platform for GitHub Copilot Chat and Claude Code conversations. Watches VS Code sessions, records every prompt / response / tool call / file edit, and stores them in a searchable Postgres-backed dashboard. Built for compliance, audit, and team knowledge preservation.
TypeScript · React 19 · Express 5 · PostgreSQL 17 · Docker
MAML for Scientific Claim Detection · MAML in NLP Model-Agnostic Meta-Learning applied to low-resource NLP tasks — few-shot adaptation for claim verification.
Twin Delayed Stochastic Actor-Critic (TD-SAC) Companion code to my Neural Computing & Applications (2023) paper. Stochastic off-policy actor-critic with twin-delayed critic updates.
- A hybrid LSTM-GRU model for stock price prediction. IEEE Access, vol. 13 (2025), pp. 117594–117618. ISSN 2169-3536. DOI:10.1109/ACCESS.2025.3586558
- Explainable Large Language Models in Healthcare Applications, Springer, 2026. Contributed chapter: Legal and Regulatory Considerations (Ch. 11, pp. 287–299). DOI:10.1007/978-3-032-15088-2_11
- Twin Delayed Stochastic Actor-Critic. Neural Computing and Applications, June 2023. DOI:10.21203/rs.3.rs-3041837/v1
- CypherRAG — Teaching LLMs to Query Knowledge Graphs for Graph-Retrieval-Augmented Generation. In preparation — method validated, manuscript drafting.
- Instructor — Large Language Models Course, Spring 2026. Science & Research Branch, Azad University, Tehran. Course materials:
SRB-University-LLM-Course-Spring-2026. - Contributor — mem0ai. Memory layer for AI agents.
- 45+ public repositories across agentic AI, RAG, RL, meta-learning, and optimization.
Agents, LLMs & Retrieval
Backend, Data & Infra
Open to senior agentic AI / LLM engineering roles — US remote and relocation.