09/11/2026 updated


100 % available
Senior Full Stack AI Engineer
Dublin, Ireland
Only remote
Bachelor's Degree in Computer ScienceAbout me
Senior Full-Stack AI Engineer, 8+ yrs; 2.5+ yrs AI/LLM serving. At ElevenLabs scaled TTS/agents for millions, cut latency 20–40%. At Microsoft improved Azure OpenAI p99 TTFT 45–65%. Mentors 3–4 engineers.
Tailwind CSSGCPHTMLJavaScriptC++/CLICascading Style Sheets (CSS)DjangoPython (Programming Language)PostgreSQLMongoDBMySQLNode.jsRedisNext.jsSQL Databases
AI/LLM Serving Infrastructure
Expertise in designing and scaling large-scale AI and LLM serving infrastructure, including real-time Text-to-Speech systems, multi-region request routing, GPU serving strategy, and low-latency WebSocket streaming endpoints serving millions of users.
Backend Development & Cloud Engineering
Proficiency in Python, Go, C++, TypeScript/Node.js, REST APIs, and WebSockets, combined with deep experience in cloud platforms such as Microsoft Azure, AWS, and GCP, as well as Kubernetes, Docker, Terraform, and CI/CD pipelines for multi-region deployments.
Reliability Engineering & Observability
Strong background in reliability engineering for critical model-serving paths, including distributed tracing, high-cardinality metrics, admission control, retry hardening, canary releases, and A/B evaluation practices to improve p99 latency and system stability.
Database & Data Systems
Experience with PostgreSQL, Redis, Microsoft SQL Server, Firebase/Firestore, caching strategies, and query optimization for high-throughput production environments.
Frontend & Client Integration
Knowledge of React, Next.js, Angular, and Vue for building streaming client playback and real-time UX integrations, including client-side audio playback with TypeScript.
Asynchronous Job Processing & ML Pipeline Integration
Development of asynchronous batch processing systems using SQS and Celery-style workers, GPU coordination, and ML model inference integration for large-scale transcription and AI workloads.
Data Platform & Backend Services
Building backend services and APIs using Scala and Python, orchestrating data processing jobs on Apache Spark, and designing data and metadata layers with MongoDB and PostgreSQL for multi-tenant data science platforms.
Mentoring & Technical Leadership
Mentoring of 3-4 engineers on inference optimization, streaming UX, and observability, with ownership of technical documentation, hiring support, and onboarding during periods of rapid team growth.
Expertise in designing and scaling large-scale AI and LLM serving infrastructure, including real-time Text-to-Speech systems, multi-region request routing, GPU serving strategy, and low-latency WebSocket streaming endpoints serving millions of users.
Backend Development & Cloud Engineering
Proficiency in Python, Go, C++, TypeScript/Node.js, REST APIs, and WebSockets, combined with deep experience in cloud platforms such as Microsoft Azure, AWS, and GCP, as well as Kubernetes, Docker, Terraform, and CI/CD pipelines for multi-region deployments.
Reliability Engineering & Observability
Strong background in reliability engineering for critical model-serving paths, including distributed tracing, high-cardinality metrics, admission control, retry hardening, canary releases, and A/B evaluation practices to improve p99 latency and system stability.
Database & Data Systems
Experience with PostgreSQL, Redis, Microsoft SQL Server, Firebase/Firestore, caching strategies, and query optimization for high-throughput production environments.
Frontend & Client Integration
Knowledge of React, Next.js, Angular, and Vue for building streaming client playback and real-time UX integrations, including client-side audio playback with TypeScript.
Asynchronous Job Processing & ML Pipeline Integration
Development of asynchronous batch processing systems using SQS and Celery-style workers, GPU coordination, and ML model inference integration for large-scale transcription and AI workloads.
Data Platform & Backend Services
Building backend services and APIs using Scala and Python, orchestrating data processing jobs on Apache Spark, and designing data and metadata layers with MongoDB and PostgreSQL for multi-tenant data science platforms.
Mentoring & Technical Leadership
Mentoring of 3-4 engineers on inference optimization, streaming UX, and observability, with ownership of technical documentation, hiring support, and onboarding during periods of rapid team growth.
Experience
Professional experience5 - 10 years
Freelancer since2014
Languages
EnglishNative speaker
Project history
Designed and scaled real-time and long-form speech infrastructure across streaming, multi-region serving, and cross-product integration. Owned the shared model abstraction and multi-model routing layer, shipped low-latency WebSocket streaming endpoints, directed multi-region request routing, led GPU serving strategy, established observability practices, and mentored 3-4 engineers on inference optimization and streaming UX.
Led reliability engineering on the Azure OpenAI Service GPT-3.5/GPT-4 model-serving path. Diagnosed and eliminated multi-region retry-storm patterns, re-architected the C++ serving layer for continuous in-flight batching and capacity-aware routing, hardened admission control and retry behavior across Go and Python services, and strengthened the control plane with capacity signaling and p99 latency alerting.
Developed and evolved production systems for AssemblyAI's batch transcription API including ingestion, preprocessing, job orchestration, model inference integration, and API delivery using Python and Go. Optimized asynchronous job processing and GPU coordination, reducing average turnaround time 30-40%, and designed internal and customer-facing dashboards for job monitoring and usage analytics.