Software Engineer, Fireworks AI

• Bachelor’s degree in Computer Science, Engineering, or a related field
• 3+ years of experience as a backend or infrastructure engineer, ideally supporting ML/AI systems or data-intensive workloads
• Experience with PyTorch and deep learning frameworks for inference and training
• Strong programming skills in Python and/or Go, with a track record of building reliable distributed backend systems
• Experience with cloud platforms (e.g., AWS, GCP), infrastructure-as-code tools (e.g., Terraform), and containerization/orchestration tools (e.g., Docker, Kubernetes)

Desirable

• We're looking for a strong Backend Infrastructure Engineer to help accelerate our multimedia AI capabilities
• You'll build and optimize the infrastructure powering state-of-the-art multimodal AI including vision-language models (VLMs), and speech AI models
• You'll focus on achieving industry-leading latency and throughput across diverse multimedia workloads
• You'll develop infrastructure for features like VLM fine-tuning, real-time voice processing pipelines, and model enablement on the latest hardware
• You'll be instrumental in helping us capture significant ARR growth in the multimedia AI space while ensuring we deliver the fastest, most reliable multimodal platform in the market
• Collaborate with ML engineers and researchers to productionize models and support evolving multimedia capabilities
• Identify, profile and address performance bottlenecks across the stack, from media preprocessing to vision/audio encoders to the core inference engine
• Ensure high reliability, observability, and security across backend systems
• Own the enablement and optimization of new model releases, ensuring we consistently deliver the fastest implementations in the market
• Build and maintain performant APIs and services
• Collaborate closely with customers and sales teams to implement custom features and optimizations that drive ARR growth
• Propose new roadmap items based on customer needs