Backend Engineer, LLM Infrastructure at Inception – San Mateo, California

Description Inception creates the world’s fastest, most efficient AI models. Our Mercury model is the world’s fastest reasoning LLM and first commercially available diffusion LLM, delivering 5x greater speed and efficiency than today’s LLMs, with best-in-class quality.
We are the AI researchers and engineers behind such breakthrough AI technologies as diffusion models, flash attention, and DPO.
We seek experienced Backend Engineers to build the core infrastructure and services that power our cutting-edge AI. In this role, you will design and develop scalable backend systems that enable seamless integration of our diffusion LLMs with enterprise applications and that support our training efforts. You'll architect high-performance systems capable of handling billions of requests while ensuring reliability, security, and optimal response times. Working closely with our ML engineers, you'll build the bridge between state-of-the-art AI models and production-ready services.
Key Responsibilities

• Design and implement scalable backend services for model serving, request routing, and load balancing
• Develop robust data pipelines and event-driven systems for monitoring of the entire tech stack
• Create backend infrastructure for experiment tracking, model versioning, and performance monitoring
• Establish authentication, authorization, rate limiting, and other security measures for enterprise-grade deployments
• Design and maintain database schemas, caching strategies, and data storage solutions
• Implement infrastructure as code, deployment automation, and CI/CD pipelines
• Collaborate with ML engineers to optimize model serving infrastructure and inference pipelines

Qualifications

• BS/MS/PhD in Computer Science, Machine Learning, or related field (or equivalent experience)
• 5+ years of experience building production backend systems
• Strong proficiency in Python, including async programming and concurrent systems
• Deep understanding of distributed systems, microservices architecture, and API design principles
• Familiarity with Kubernetes, CI/CD pipelines, and cloud infra (AWS & Azure).
• Experience with both SQL and NoSQL databases (e.g., Neon)
• Strong understanding of system design, scalability patterns, and performance optimization
• Interest in a fast-paced startup environment

Preferred Skills

• Experience building backends for AI/ML systems
• Experience with monitoring and observability tools (e.g., Prometheus and Grafana)
• Understanding of ML concepts and experience with ML frameworks (PyTorch, TensorFlow)
• Experience with infrastructure as code tools (e.g., Terraform)
• Experience with testing frameworks and test-driven development
• Experience with high-scale systems handling millions of requests per day

Why Join Inception

• Work with World-Class Talent: Collaborate with the inventors of diffusion models and leading AI researchers
• Shape Foundational Technology: Your decisions will influence how the next generation of AI products are built and used
• Immediate Impact: Join at the ground floor where your contributions directly shape product direction and company trajectory

Perks & Benefits

• Competitive salary and equity in a rapidly growing startup.
• Access to the latest GPU hardware and cloud resources
• Flexible vacation and paid time off (PTO).
• Health, dental, and vision insurance.
• A collaborative and inclusive culture

About UsInception creates the world’s fastest, most efficient AI models. Today’s autoregressive LLMs generate tokens sequentially, which makes them painfully slow and expensive. Inception’s diffusion-based LLMs (dLLMs) generate answers in parallel. They are 5x faster and more efficient, while delivering best-in-class quality.
Inception was co-founded by Stanford professor Stefano Ermon, who co-invented such breakthrough AI technologies as diffusion models, flash attention, and DPO, UCLA professor Aditya Grover, who co-invented node2vec, decision transformers, and d1 reasoning, and Cornell professor and Afresh co-founder Volodymyr Kuleshov, who co-invented MDLM and Block Diffusion.
We pioneered the application of diffusion to language, launching the world’s first commercially available dLLM, Mercury, in early 2025. We are currently deploying our large-scale diffusion LLMs at Fortune 500 companies. Diffusion is the technology behind today’s image and video AI, and we’re making it the standard for LLMs as well.
Our team includes engineers from Google DeepMind, Meta AI, Microsoft AI, and OpenAI. Based in Palo Alto, CA, we are backed by A-list venture capitalists, including Menlo Ventures, Mayfield, M12 (Microsoft’s venture fund), Snowflake Ventures, Databricks, and Innovation Endeavors, and by tech lumaries such as Andrew Ng, Andrej Karpathy, and Eric Schmidt.
If you are talented, innovative, and ambitious, come help us invent the future of AI.
We are an equal opportunity employer and encourage candidates of all backgrounds to apply.