Open to opportunities

Sergiu Nicoara

@sergiunicoara

Message

AI Engineer specializing in production-grade LLMs, agentic systems, and scalable RAG pipelines.

Romania

Message

What I'm looking for

I seek roles building production-grade LLM and agentic systems with emphasis on scalability, observability, cloud-native deployment, and rigorous evaluation frameworks.

I am an AI Engineer with 10+ years of enterprise engineering experience and a strong focus on production-grade LLM applications, agentic systems, deterministic multi-agent orchestration, and scalable RAG pipelines. I have built and deployed 10+ end-to-end AI systems to cloud platforms, implementing persistent memory, trajectory logging, and LLM-as-a-Judge evaluation frameworks to ensure reliability and grounded generation.

My background includes engineering high-availability telecom systems serving 10M+ users and leading STEM education initiatives. I design observable, scalable solutions using modern LLM architectures and robust software engineering practices, delivering cloud-native deployments with Docker, Kubernetes, CI/CD, Google Cloud Run, Vertex AI, and AWS SageMaker.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer

Current

Independent

Jan 2025 - Present (1 year 1 month)

Built and deployed 10+ production-grade LLM and agentic systems with deterministic multi-agent orchestration, scalable RAG pipelines, persistent memory, and LLM-as-a-Judge evaluation frameworks.

LangGraph AutoGen LlamaIndex Vector Search Docker Kubernetes Google Cloud Run

Homeschooling Educator

Independent Technologist

Sep 2016 - Dec 2024 (8 years 3 months)

Led STEM homeschooling programs with multi-year curricula in mathematics and computer science and implemented assessment frameworks with measurable learning outcomes.

Curriculum Design Project Based Learning STEM Education Student Evaluation

Software Engineer

Alcatel-Lucent Romania

Sep 2005 - Sep 2016 (11 years)

Engineered high-availability telecom backend platforms serving 10M+ users with 99.9% uptime, delivering scalable, fault-tolerant systems for international deployments.

High Availability Distributed Systems Performance Optimization Fault Tolerance Backend Engineering Scalability