AI Engineer — LLM Systems · Agentic AI · Production Deployment
Agents, not chatbots. I build agentic systems that plan, call tools, and execute multi-step workflows — function calling, MCP servers, and multi-agent orchestration over real enterprise data.
Production over prototypes. I own the full lifecycle: Python services → LLM integration → containerized deployment on AWS → monitoring, evals, and usage analytics.
Enterprise constraints. My systems survive real-world requirements: compliance, security reviews, cost control, and non-technical end users.
LLM_SYSTEMS |
AGENTIC_AI |
ENGINEERING |
|---|---|---|
| RAG pipelines & vector search | Multi-agent orchestration | Python services · FastAPI |
| Prompt engineering & evals | Tool use / function calling | Docker & containerization |
| Structured outputs & context mgmt | MCP — Model Context Protocol | AWS · ECR · App Runner |
| Claude API · OpenAI API | Agent evaluation & guardrails | Monitoring & usage analytics |
CORE ENGINEERING
AI / LLM TOOLING
ANALYTICS & DATA
# The pattern behind every agentic system I ship
async def run_agent(task: Task) -> Result:
context = retrieve(task, vector_store) # RAG: ground the model in real data
plan = llm.plan(task, context) # reasoning before acting
for step in plan:
tool = registry.resolve(step) # tool use via MCP servers
result = await tool.execute(step.args) # typed, validated I/O
context.update(result) # feedback loop
return evaluate(context.output) # evals + guardrails before delivery| Certification | Provider | Year |
|---|---|---|
| AWS Certified Cloud Practitioner (CLF-C02) | Amazon Web Services | 2026 |
| AWS Certified AI Practitioner (AIF-C01) | Amazon Web Services | 2026 |
| OCI Generative AI Professional | Oracle | 2025 |
| OCI Data Science Professional | Oracle | 2025 |
| Certified in Cybersecurity (CC) | ISC² | 2025 |
| Digital Transformation Management | Arizona State University | 2024 |
| Data Science Practitioner · AI Practitioner | IBM | 2024 |
| Alteryx Designer Core | Alteryx | 2024 |
| Google Data Analytics Professional | 2023 |
def build(problem):
"""How I approach every AI system."""
solution = (
understand(problem) # business context before code
.simplify() # smallest architecture that works
.ship_early() # production feedback > perfect prototypes
.measure() # if it's not monitored, it's not done
)
return solution # reproducible · documented · owned end-to-end
