We’re looking for a Python Engineer with a passion for AI and a knack for building high-performance, low-latency systems. You’ll work in a fast-paced environment within our AI-native team, helping power Telnyx AI, our cutting-edge platform delivering intelligent communication tools through speech, embeddings, and scalable inference infrastructure.

This is an exciting opportunity to help shape TelnyxAI from the ground up. You’ll collaborate with the wider team here to integrate open-source LLM tools and build scalable microservices that make AI accessible, reliable, and real-time.

The Opportunity

Our Python team builds highly available, low-latency microservices using bleeding-edge technologies. This role focuses on developing our AI applications and infrastructure, from model deployment to product-facing APIs, with a particular emphasis on text and voice interfaces.

You’ll be hands-on in:

• Designing developer-friendly APIs to interact with inference and embeddings services
  
  
• Building internal tools and services to streamline AI workflows across teams
  
  
• Creating integrations between our Storage and Voice APIs and LLM-based systems
  
  
• Applying distributed computing tools like Ray to deploy, scale, and optimize ML models
  
  
• Keeping TelnyxAI at the forefront of modern AI/ML trends and best practices
  
  

What You’ll Do

• Build, test, and deploy scalable Python microservices for AI inference and text/voice processing
  
  
• Develop APIs and internal tools that make AI easy to use across our product ecosystem
  
  
• Optimize performance and latency in production environments
  
  
• Continuously evaluate and integrate emerging AI technologies and LLM frameworks
  
  
• Collaborate with cross-functional teams (Product, Infra, ML) to bring features from ideation to production
  
  
• Troubleshoot, debug, and monitor critical systems in production
  
  
• Participate in code reviews and uphold high-quality engineering standards
  
  

Who We’re Looking For

• 3+ years of professional software development experience in Python
  
  
• Strong grasp of async Python frameworks (e.g. FastAPI, Starlette)
  
  
• Experience with web app development and microservice architecture
  
  
• Comfortable working with relational databases at scale
  
  
• Familiar with LLM frameworks and tools (e.g. PyTorch, Transformers, DeepSpeed, vLLM)
  
  
• Experience deploying and maintaining ML models in production environments
  
  
• Understanding of scalable, distributed systems
  
  
• Excellent communication skills and the ability to work cross-functionally
  
  

Nice To Haves

• Familiarity with Ray (Ray Core, Serve, Train) or similar distributed frameworks
  
  
• Experience with cloud-native stacks (e.g. Docker, Kubernetes, Prometheus, Jaeger)
  
  
• Knowledge of LLM optimization techniques (e.g. quantization, speculative decoding)
  
  
• Background in Retrieval Augmented Generation (RAG) systems
  
  
• Experience with AMD ROCm or other GPU stacks
  
  
• Passion for staying ahead of the curve in AI and machine learning
  
  

Why You’ll Love It Here

At Telnyx, we’re not just building products—we’re building the future of intelligent communication. Our TelnyxAI platform empowers developers and businesses to:

• Store and serve vector embeddings at scale
  
  
• Use open-source models with our hosted inference infrastructure
  
  
• Deploy multimodal AI features across text, voice, and storage seamlessly
  
  

You’ll have the autonomy to take ownership of meaningful projects, contribute ideas that shape the product roadmap, and collaborate with talented people who care about impact.

#LI-KG1
#LI-DUBLIN