Open to opportunities

Nicholas Keenan

@nicholaskeenan

Message

Senior AI/ML engineer building production LLM, RAG, and low-latency voice systems.

United States

Message

What I'm looking for

I’m looking to build scalable, observable LLM/AI products with strong engineering practices—RAG, evaluation, and low-latency inference—backed by distributed systems and cloud infrastructure I can own end-to-end.

I’m a senior AI/ML engineer with 9+ years building production machine learning and LLM-powered systems across finance, insurance, and enterprise SaaS. I deliver end-to-end AI solutions—data pipelines, model training and fine-tuning, RAG architectures, and real-time inference—while keeping performance, reliability, and compliance at the core.

I’ve deployed large-scale conversational AI with scalable, observable infrastructure using Python, FastAPI, Django, Docker, Kubernetes, and cloud platforms like GCP and AWS. From MCP-based LLM-agent integrations and voice AI pipelines to evaluation and latency/accuracy trade-off monitoring, I translate machine learning capabilities into real-world products through strong architecture, automation, and engineering discipline.

Experience

Work history, roles, and key accomplishments

Current

Senior Software Engineer / Technical Lead

Current

Gail

Oct 2023 - Present (2 years 6 months)

Fine-tuned Llama 3.3 with LoRA on Vertex AI and built end-to-end RAG pipelines using LlamaIndex, Pinecone embeddings, and retrieval evaluation for financial Q&A and document intelligence. Deployed low-latency inference services with FastAPI and Kubernetes and implemented agentic integrations via an MCP layer plus voice AI pipelines.

LoRAs Vertex AI LlamaIndex Pinecone fastAPI Kubernetes ONNX Runtime LangGraph OpenTelemetry

Senior Software Engineer / Technical Lead

Lula Technologies, Inc.

Oct 2021 - Oct 2023 (2 years)

Built API-driven insurance workflows and a driver-risk decisioning ML pipeline using FastAPI, scikit-learn, and XGBoost with real-time inference on GKE and Pub/Sub. Shipped AI-assisted claims triage and claims/policy services, improved multilingual classification accuracy by 10%, and added observability with OpenTelemetry to keep p99 latency under 200ms and errors below 0.01%.

TypeScript fastAPI scikit learn XGBoost Flan T5 GKE Google Cloud Pub Sub Terraform OpenTelemetry

Senior Software Engineer

Taxfyle

May 2019 - Oct 2021 (2 years 5 months)

Developed C#/.NET backend services and APIs for firm onboarding and operational workflows using PostgreSQL-backed transactional systems. Built ML-powered document automation with PyTorch and spaCy to extract tax data and cut manual effort by accelerating return processing by 40%.

C# .NET PostgreSQL Python PyTorch SpaCy CI CD Terraform Kubernetes Go REST APIs

Software Engineer Internship

Taxfyle

May 2017 - May 2019 (2 years)

Engineered iOS/Android mobile features using C#/Xamarin and React Native and supported QA with Jest and test workflows across 30+ app features. Built Python internal tools and automation scripts to clean, reconcile, and support scalable mobile app operations.