~/deployedengineer ~
$ whoami
Senior AI Engineer. Recovering over-engineer. LLM whisperer.
$ cat /etc/motto
Ship it. Eval it. Ship it better.
$ ls ./superpowers
agentic_systems/  rag_pipelines/  stakeholder_wrangling/  coffee_dependency.py
$ cat coffee_dependency.py
while not deployed: coffee += 1  # O(∞)
$ echo $STATUS
open to opportunities. let's build something.
[ press ESC or click to close ]
Projects Experience Stack Contact
Senior AI Engineer

Ahmed.currently: open to work ✦

I build production-grade LLM systems, multi-agent architectures, and agentic workflows that ship — not just demo. 6+ years taking AI from whiteboard to deployed infrastructure at companies like Vanguard, TXU Energy, and Yellow AI.

LangGraph// graph state that actually persists LangChain// before it was cool CrewAI// agents arguing with each other productively AWS Bedrock// enterprise LLMs, enterprise patience MCP// stdio → StreamableHTTP, been there RAG Pipelines// retrieval that actually retrieves Vertex AI// Gemini + reranking = chef's kiss FastAPI// pydantic is non-negotiable Python// home TypeScript// types or chaos. usually both. Multi-Agent Systems// orchestration > vibes GCP// Cloud Run is genuinely great
6+
Years building
AI systems
70%
Cost reduction
via ML migration
10x
Analytics pipeline
speed-up
0.95
RAG eval score
in production
01
Real-time System
TaskFlow

Real-time collaborative task management with append-only event sourcing, WebSocket delta sync, and AI task suggestions powered by OpenRouter and Anthropic in parallel. Built in Go + Next.js with optimistic locking, undo/redo, presence awareness, and Redis pub/sub for multi-instance fan-out.

GoNext.js 14WebSocketsPostgreSQLRedis pub/subAnthropic APIOpenRouterDocker ComposeTypeScript
Event-sourced
Append-only log + undo/redo
Dual-LLM
OpenRouter ∥ Anthropic race
~10 req/s
Rate limited per user
02
Stealth Startup
Software Engineer — Agentic AI
11/2025 – 04/2026
  • Built LangGraph multi-agent graph with Postgres checkpointing + Redis session state
  • Delivered MCP server/client integrations over stdio and StreamableHTTP
  • Established RAG evaluation loop with Langfuse tracing for regression tracking
  • Embedded with execs: scoped POC → production handoff with full runbooks
Vanguard
Software Engineer — AI/GenAI
09/2024 – 10/2025
  • Led GenAI initiatives from internal demo to accepted enterprise rollout
  • Deployed LLMs via AWS Bedrock integrated with DynamoDB at scale
  • A/B tested multi-agent MCP architectures with segmented employee groups
  • Coordinated rollout across 5 stakeholder groups
Outlier AI
Software Engineer — LLM Evaluation
01/2024 – 08/2024
  • Improved LLM code generation accuracy across Python, Java, JavaScript, Go
  • Applied chain-of-thought and ReAct prompting — reduced hallucinations measurably
  • Generated training data supporting RLHF reward model optimization
TXU Energy
Software Engineer — Data/AI
01/2023 – 12/2023
  • Reduced licensing costs 70% migrating SAS → Python + AWS Lambda/Glue
  • Cut analytics processing from 20+ hrs to under 2 hrs via cloud-native ETL
  • Built churn prediction model with strong accuracy on behavioral + temporal data
Yellow AI
Software Engineer — Conversational AI
06/2019 – 12/2021
  • Improved customer verification to 98% accuracy with deep learning ID scan
  • Increased client revenue 20% via automated analytics microservices
  • Scaled enterprise chatbot deployment across ITSM and customer service environments
Education
MS Computer Science
UT Arlington · 2023
BTech Computer Science
JNTU · 2019
Oracle Cloud Infrastructure — GenAI Certified
HarvardX Data Science Professional
03
AI / LLM
LangChainLangGraphCrewAIMCPRAGRAGASDeepEvalLangfuseOpenTelemetryPrompt EngineeringRLHFReAct
Cloud / Infra
AWS BedrockAWS LambdaAWS GlueS3GCP Vertex AICloud RunCloud BuildTerraformDockerKubernetesCI/CDSecret Manager
Languages / Frameworks
PythonTypeScriptGoNode.jsSQLFastAPIFlaskNext.jsPydanticpytestOpenAPIWebSocketsSSE
Data / Vector / Stores
QdrantPostgreSQLRedisBigQuerySnowflakeMongoDBDynamoDBElasticsearchAlembic
Let's
build.

Open to senior AI engineering and Forward Deployed Engineer roles at companies shipping real AI products. I move fast, own systems end-to-end, and care about what gets deployed — not just what gets demoed.

30 characters minimum
or reach out directly