Anuoluwa Olutayo
AI Engineer
Dallas, Texas
you@example.com

I take AI systems from development to secure, production-ready deployments.

I take AI and LLM systems from a working build to a release a team can trust. The work is integration, cloud deployment, MLOps, and DevSecOps: CI/CD, containers, Kubernetes, monitoring, and the security controls around production.

EXPERIENCE
AI Engineer — YOUR COMPANY (2025 — Present)
Taking LLM systems from a working build to a secured, observable deployment other teams can run.
- Shipped a document assistant with citations, tracing, and a release gate.
- Put evaluation in CI so a prompt change cannot ship on a single example.
- Traced every tool call so failures are visible without reading raw logs.
Python, LangGraph, FastAPI, PostgreSQL, Docker

MLOps Engineer — YOUR COMPANY (2024 — 2025)
Owned the path around existing models: packaging, promotion, rollout, and the monitors that say whether the service is healthy.
- Replaced a manual handoff with a pipeline that promotes one container digest.
- Kept a previous release ready so rollback did not depend on the person who packaged it.
- Tied latency and error alerts to the release that was actually live.
Docker, Kubernetes, GitHub Actions, MLflow, AWS

DevSecOps Intern — YOUR COMPANY (2023 — 2024)
Supported CI, containers, and the checks that keep a service from shipping with known gaps.
- Added image scans and secret checks to a pipeline that previously only built.
- Documented the environment setup so the next deploy did not start from a laptop.
Docker, GitHub Actions, Terraform, Linux

EDUCATION
B.S. Computer Science, YOUR UNIVERSITY (2021 — 2025) — YOUR EDUCATION — coursework in software systems, cloud infrastructure, and security.

PROJECTS
Citation Desk — Answers grounded in your documents, with page-level citations.
A retrieval pipeline routes each question to uploaded documents or a web fallback, streams the steps, and cites the file, page, and passage used to write the reply.
Next.js, FastAPI, LangGraph, pgvector, Python

Route Agent — Multi-step workflows with a visible plan and a stop condition.
A planner proposes a short tool sequence, executes it with budgets, and writes a final brief that links each claim back to a tool result.
LangGraph, Python, FastAPI, PostgreSQL, OpenAI

Platform Lane — Kubernetes, environments, and a release an LLM service can actually run on.
A deployment lane that builds the image, promotes it through environments, and runs it on Kubernetes with secrets, probes, and a rollback.
Kubernetes, Helm, Terraform, Docker, GitHub Actions

Release Ops — Promotion, rollout, and alerts for an AI service already in use.
A release path that versions the artifact, deploys it on a schedule, watches latency and errors, and pages when the live service leaves its expected range.
GitHub Actions, Docker, MLflow, Kubernetes, Prometheus

Guardrail Studio — A small eval suite for tone, grounding, and unsafe replies.
A suite of tagged cases runs on every prompt change and blocks the release when grounding or safety scores drop.
Python, FastAPI, Next.js, LLM evals

SKILLS
LLM Systems: LangChain, LangGraph, RAG, Agents, Evals, FastAPI, Streaming, pgvector
MLOps: CI/CD, MLflow, Model serving, Rollouts, Registries, Release gates
Cloud & Infrastructure: AWS, Kubernetes, Helm, Docker, Terraform, Linux
DevSecOps: Image scanning, Secret management, IAM, Pipeline security, SBOM, Least privilege
Observability: Prometheus, Grafana, OpenTelemetry, Logging, Alerting
Languages: Python, TypeScript, Bash, SQL
Backend & APIs: FastAPI, Next.js, REST, PostgreSQL, Redis