mehran@dashti:~$

ΤΕΧΝΗ · Tunoo (Germany) · Remote

Mehran Dashti

Senior Software Engineer — AI & Distributed Systems

agent · session live
▸ orchestrator spawn 4 agents
▸ tools retrieval · sql · http · queue
▸ memory redis vector store ok
▸ p95 latency 186ms · 10+ tenants
▸ ready
Experience10+ years · fintech, e-commerce, logistics, AI
CurrentlySeeking senior backend / staff engineer roles
LinksGitHubLinkedInEmail
MicroservicesEvent SourcingCQRSFastAPILaravelLLM IntegrationAI AgentsKubernetesRabbitMQgRPCRedisMongoDB

whoami

Profile

Senior Software Engineer with 10+ years delivering high-scale distributed systems across fintech, e-commerce, logistics, and AI.

Led decomposition of a large production monolith into 10+ independently deployable microservices at LiaServices. Built Iran's first Agent-as-a-Service platform at Delaverse (Jan 2025 – Apr 2026). Deep expertise in event-driven architecture, LLM integration, and high-throughput API design. Currently seeking senior backend or staff engineer roles at high-scale product companies in Tehran or remote.

10+
Microservices shipped
99.9%
Payment uptime
10k
Requests / min peak
60k+
Users served

systemctl status agent-pipeline

Agent Systems

How the Agent-as-a-Service platform routes a request.

  1. 01
    Intent
    Versioned REST entry, auth & tenant resolution.
  2. 02
    Orchestrator
    Plans the run, selects agents, splits the workflow.
  3. 03
    Tools
    Plugin system — retrieval, HTTP, SQL, queue workers.
  4. 04
    Memory
    Redis-backed state and conversation context per tenant.
  5. 05
    Response
    Streamed output, traced and monitored in real time.
Multi-agent
Orchestration engine with plugin system and workflow pipeline.
LLM integration
OpenAI API in production — Persian language support end to end.
Observability
Real-time monitoring dashboard, sub-second agent response times.

git log --graph --all

Experience

Ten years of systems in production.

4 roles · 20 systems
2016 → present
6062c21(HEAD -> main, origin/tunoo)
langgraph · multi-agent
Now

Tunoo

AI Software Engineer
Germany · Remote
Present
active
LangGraphRAG · MilvusPII safety

Tunoo AI — Multi-Agent AI Platform. Architected and built a production-grade multi-agent AI platform using LangGraph for orchestrating complex agent workflows in Python.

  1. 75bc76fAgent Orchestration

    Designed the agent orchestration flow, managing control and data flow between agents to improve reliability and reduce failure cascades.

    Python · LangGraph
  2. 16b1626Prompt Injection Defense

    Implemented prompt injection defense, detecting and rejecting malicious or adversarial input before it reached downstream agents.

    Python · LangGraph
  3. 273156dVector Search

    Improved Milvus vector search performance, tuning indexing and retrieval configuration for faster, more accurate similarity search.

    Milvus · Python
  4. 8eb3e80Embedding Service

    Built an embedding service to populate and maintain the RAG pipeline, handling document ingestion and vectorization into Milvus.

    Python · Milvus · Docker
  5. a8de2b3PII Masking Layer

    Designed and implemented a PII masking/anonymization layer using Microsoft Presidio with pseudonymization techniques to protect sensitive data across agent pipelines.

    Presidio · Python
  6. 568c5c6Spec-driven Development

    Established a spec-driven development (SDD) workflow using OpenSpec, improving requirement traceability and reducing implementation drift across features.

    OpenSpec
Tech stack: Python, LangGraph, Presidio, Milvus, MongoDB/Redis (as applicable), Docker
309ab6d(tag: v2025.26)
agent · aaas
2025–26

Delaverse

Tech Lead
Part-time
Jan 2025 – Apr 2026
archived
3 systemsp95 <200ms

Architected and built core backend for Iran's first Agent-as-a-Service (AaaS) platform — enabling businesses to deploy intelligent AI agents for complex workflow automation without engineering overhead.

  1. 5f2c8e3Multi-tenant AaaS Platform

    Built multi-agent orchestration engine, plugin system, workflow pipeline & real-time monitoring dashboard — onboarded 10+ enterprise clients with sub-second agent response times.

    Python · FastAPI · OpenAI · Docker · Redis · RabbitMQ
  2. db60436AIQ – Educational AI

    Adaptive AI assistant for children aged 7–12 with personalised learning, parental controls, content filtering, and full Persian language support — <200ms p95 latency under concurrent load.

    Python · LLM · Laravel · MongoDB · Redis
  3. f32bdffInfrastructure

    High-availability architecture for concurrent agent workloads; zero-downtime SSL/TLS renewal pipeline; versioned RESTful APIs consumed by 3+ internal teams with no breaking changes across releases.

b71ccb0(tag: v2020.25)
mesh · 10+ services
2020–25

LiaServices

Senior Software Engineer
Full-time
Jan 2020 – Apr 2025
archived
7 servicesevent-driven99.9% uptime

Core engineer in a 14-person team — led decomposition of a large production monolith into 10+ independently deployable microservices, improving release cadence from monthly to weekly with zero-downtime migrations.

  1. d7e9360Payment Service

    Multi-gateway failover with idempotent transactions & automated reconciliation — 99.9%+ uptime; zero duplicate charges across all transaction flows.

    Python · MongoDB · Docker
  2. 4c1b165API Gateway

    Internal reverse proxy routing 100% of cross-service traffic — enforced rate limiting, auth, and service discovery; reduced inter-service latency by eliminating redundant auth round-trips.

    Laravel · Redis · Docker
  3. 466307aAAA Service

    Centralised auth & accounting with LDAP integration and Redis-backed sessions — single source of truth for all 10+ services; session lookup under 5ms via Redis caching.

    Laravel · LDAP · MariaDB · Redis
  4. 856a767Warehouse Automation

    Event-driven inventory & order fulfilment processing 5,000+ orders/day at peak via RabbitMQ — decoupled producers from consumers, eliminating bottlenecks under sustained load.

    Laravel · MongoDB · RabbitMQ · Redis · S3
  5. ade51fcLMS

    Full learning platform serving part of LiaServices' 60,000+ user base — certifications, video courses & class reservations; S3-backed media delivery kept page load times under 2s for course content.

    Laravel · MongoDB · MariaDB · Redis · S3
  6. dce8ed1Ticketing

    SLA-aware smart routing engine — priority-based agent assignment cut average first-response time and ensured high-priority tickets were never left unassigned.

    Python · MongoDB · Celery · Redis
  7. 9657e16Product & Promotion

    Flexible catalogue handling 10,000 requests/minute at peak with an order placed every 3 seconds — RabbitMQ-backed async processing prevented promotion bursts from blocking the main request path.

    Python · MongoDB · RabbitMQ
afc67a2(tag: v2016.19)
bss · telecom
2016–19

Bahar Samaneh Shargh

Mid-level → Senior Backend Developer
Full-time
Jan 2016 – Dec 2019
archived
4 systemsDDD

12-person team building CRM, ERP, and BSS systems for a major Iranian ISP — complex telecom billing and provisioning for hundreds of thousands of subscribers.

  1. 9565312Billing System

    Integrated IBS, Netbill, Ava & Chakavak for automated billing & traffic quota — DDD-modelled domain handled hundreds of thousands of subscriber accounts with accurate, conflict-free expiry processing.

    DDD · Laravel · MySQL · Redis
  2. 13ecd91DSL/ADSL/VDSL Provisioning

    Full activation lifecycle from feasibility to installation — automated order pipeline reduced manual provisioning steps, cutting activation time for new subscribers.

    Yii · MySQL
  3. 94936c8Sales Agent Network

    Hierarchical multi-level agent system with automated commission & bonus calculations — eliminated manual spreadsheet reconciliation for hundreds of sales agents.

    Yii · MySQL
  4. 54476bbNotification Service

    Async multi-channel dispatcher (SMS, email, in-app) — queue-backed delivery ensured no notification loss under traffic spikes; fully decoupled from all upstream services.

    Python · MongoDB · Redis

ls -la ~/.skills

Technical Skills

The stack behind the agents.

6 domains
python · langgraph · milvus
01Languages & Runtimes
Python 3.11+ (async-first), TypeScript, SQL, Bash
02AI / LLM Engineering
LangGraph, LangChain, OpenAI API, structured outputs & schema-validated generation, multi-agent supervisor/worker orchestration, human-in-the-loop interrupt/resume, checkpointed conversational state, prompt engineering, intent routing & disambiguation, multilingual agents (DE/EN/FA/AR/TR)
03RAG & Retrieval
Milvus, BGE-M3 embeddings, hybrid semantic + lexical retrieval, reciprocal-rank fusion, weighted multi-signal reranking, relevance gating, corpus ingestion pipelines, offline retrieval evaluation (MRR, precision@k)
04AI Security
Prompt-injection defense (fencing, closed-schema extraction, hard-block chokepoints, audit logging), reversible PII masking/pseudonymization (Presidio, spaCy NER, custom recognizers), GDPR-oriented data handling, least-privilege & tenant isolation, fail-closed controls, staged rollout with kill-switch
05Backend & Distributed Systems
FastAPI, WebSocket, Kafka (event-driven architecture), Redis (leases, dedup, registry), PostgreSQL, MongoDB, S3/MinIO, idempotent operations, graceful degradation, fault isolation
06Platform & Practice
Docker, Kubernetes/OpenShift, GitLab CI/CD, SonarQube quality gates, OpenTelemetry/Langfuse tracing, structured logging, pytest (unit/contract/integration), spec-driven development, architectural documentation
07Education
B.Sc. Software Engineering — Shamsipour University · TehranOct 2015 – Oct 2019

gh repo list --source

Open Source

fastapi-milvus-sample
Retrieval-augmented generation service on FastAPI, Milvus and OpenAI — standard, conversational and LangGraph agentic RAG, with five deep-dive guides to the stack.
PythonRAG · Milvus · LangGraph
fastapi-iranian-bank-gateways
FastAPI toolkit for all 17 major Iranian payment gateways — async-first, production-ready.
PythonMITFastAPI · payments · async
fastapi-role-permission
Role & permission middleware for FastAPI with JWT auth and multi-tenant support.
PythonMITFastAPI · RBAC · multi-tenancy
fastapi-blueprint
Production-ready FastAPI scaffold — DI, DB, auth, Docker out of the box.
PythonFastAPI · dependency injection · Docker
laravel-api-response
Standardised JSON response wrapper for Laravel APIs.
PHPLaravel · REST API
laravel-api-exception
Structured JSON error handling for Laravel — consistent HTTP status codes.
PHPLaravel · error handling · REST API
More on GitHub
github.com/MehranDashti →

man hire

Hire

What I do, and how to start.

Short answers to the questions people actually ask before getting in touch.

What does Mehran Dashti do?
I am a senior software engineer specialising in multi-agent AI systems and high-scale distributed backends. Day to day that means designing LangGraph agent orchestration, building retrieval-augmented generation pipelines on Milvus, hardening LLM systems against prompt injection and PII leakage, and decomposing monoliths into event-driven services in Python and FastAPI. I have been doing backend work for over ten years and AI platform work for the last two.
Are you available for hire?
Yes. I am open to senior backend, staff engineer and AI engineering roles, and to consulting engagements. I work remotely from Tehran with teams in Europe and worldwide, and I currently work remotely for a German company, so distributed collaboration across time zones is normal for me rather than an experiment.
What kind of engagements do you take?
Three shapes. Full-time senior or staff engineering roles. Fractional or part-time work on an AI platform, typically one to three days a week. And short scoped consulting: an architecture review of an agent system, a RAG pipeline that is returning poor results, an AI security assessment covering prompt injection and PII handling, or a monolith decomposition plan. Scoped work usually runs two to six weeks.
Can you help with AI security and data protection?
That is one of my core areas. I have implemented prompt-injection defense in production — fencing, closed-schema extraction, hard-block chokepoints and audit logging — and designed a reversible PII masking and pseudonymization layer with Microsoft Presidio, spaCy NER and custom recognizers, applied across agent pipelines with tenant isolation and fail-closed controls.
What is your experience with RAG and vector search?
I build and tune retrieval systems on Milvus: BGE-M3 embeddings, hybrid semantic and lexical retrieval, reciprocal-rank fusion, weighted multi-signal reranking and relevance gating, with offline evaluation using MRR and precision@k. I also built the embedding and ingestion service that keeps such a pipeline current. There is a working reference implementation in my fastapi-milvus-sample repository if you want to read the code before you talk to me.
Which languages do you work in?
Persian is my first language, I work professionally in English, and I have working German. Technically I write Python and TypeScript day to day, with PHP and Laravel from earlier years, and I have shipped multilingual agent systems covering German, English, Persian, Arabic and Turkish.
How do I get in touch?
Email mehran19.md@gmail.com with a paragraph on the problem and the constraints. I reply to concrete enquiries within a day or two. If it is a fit I will suggest a call; if it is not, I will say so and point you somewhere better.
mail mehran19.md@gmail.com

bash

Shell

Ask it anything the CV knows.

Mehran Dashti — interactive shell
locale en · type a command, or tap one below
 
mehran@dashti:~$ whoami
Mehran Dashti
Senior Software Engineer — AI & Distributed Systems
 
AI Software Engineer @ Tunoo — Germany · Remote
10+ years · fintech, e-commerce, logistics, AI
 
mehran@dashti:~$ help
available commands
help list every command
whoami who I am and what I do
ls [work/] list sections, or the roles under work/
cat <role> read one role in full
skills the technical domains
hire availability and how to engage
faq [n] questions people ask before getting in touch
contact email, phone, github, linkedin
open <target> open github | linkedin | email
uname -a system information
neofetch the obligatory ASCII readout
history commands entered this session
clear clear the screen
sudo <anything> escalate (it will not work)
 
tip: ↑ and ↓ walk through history

mail -s "hello" mehran

Let's build
something durable.

Open to senior backend and staff engineer roles — Tehran or fully remote.

Emailmehran19.md@gmail.comPhone+98 919 720 8607Phone · 2+98 939 055 1986GitHubMehranDashtiLinkedInin/mehran-dashti