- 🧠 AI Systems Engineer (LLMs, RAG, Agents)
- ⚙️ MLOps + Platform Engineering (K8s, CI/CD, MLflow)
- 📡 Data Engineering (Spark, Kafka, Flink)
- ☁️ Cloud-native AI (AWS, Azure)
- 🏗️ Built end-to-end AI systems from data → model → deployment → monitoring
I build production AI systems, not just models.
- Design RAG pipelines with retrieval + re-ranking + eval loops
- Build streaming + batch data pipelines for ML systems
- Deploy LLMs as scalable APIs with observability
- Engineer ML platforms (training → deployment → monitoring)
- Optimize systems for latency, reliability, and cost
- I combine Product Thinking + Engineering Execution
- I understand why to build, not just how
- I bridge data engineering + ML + infrastructure
- I build systems that are deployable, observable, and scalable
- 🚀 Built production-grade RAG systems with tool-calling orchestration
- ⚙️ Designed end-to-end ML pipelines (data ingestion → inference APIs)
- 📉 Reduced system complexity via modular AI microservices architecture
- 📡 Worked with real-world data pipelines (batch + streaming)
- 🧪 Applied causal ML for decision systems (policy-level impact)
LLMs RAG Agentic AI LangChain Causal ML (EconML) Evaluation Pipelines
Apache Spark Apache Kafka Apache Flink
ETL / ELT Feature Pipelines Data Modeling
Kubernetes Docker MLflow Terraform
CI/CD (GitHub Actions, Jenkins)
AWS (S3, EKS, SageMaker, Bedrock)
Azure AI (Azure ML, AI Studio)
Python FastAPI Go REST APIs
Prometheus Grafana ELK Stack
🔗 https://github.com/SyedTahaAbbas/causal-ml-for-electricity-access
- Built end-to-end causal ML pipeline
- Estimated treatment effects using EconML
- Performed robustness & sensitivity analysis
- Delivered decision-ready allocation insights
- Advanced RAG architectures (hybrid retrieval, eval systems)
- Real-time AI systems
- AI platform engineering
- Scaling LLM systems in production
If you're building:
- AI products
- Data platforms
- ML infrastructure
→ I’m open to interesting problems and collaborations.