Backend Engineer - AI
Role details
Job location
Tech stack
Job description
A1 is a self-funded AI group, operating in full stealth. We're building a new global consumer AI application where backend systems are not glue - they are the control plane that connects models, data, users, and product experiences.
This is a founding backend role. You will design and build the systems that orchestrate models, manage prompts and evaluation, and power every AI interaction users experience - under real-world constraints like latency, cost, failures, and scale.
-
You power every AI interaction users experience
-
You shape how models are orchestrated, evaluated, and improved
-
You directly affect cost, latency, and reliability
-
You build real production AI infrastructure
-
Design and implement backend services for AI-powered apps
-
Integrate LLMs, vision, speech, and other models
-
Build orchestration pipelines (agents, tools, workflows)
-
Implement prompt management and versioning
-
Build evaluation, logging, and feedback systems
-
Design scalable APIs for mobile and web clients
-
Handle retries, caching, rate limits, and fallbacks
-
Ensure security, privacy, and cost control
Requirements
-
4+ years backend engineering experience
-
Hands-on AI model integration experience
-
Strong proficiency in Python, Node.js, or Go
-
Experience designing REST/gRPC APIs
-
Understanding of AI latency and cost tradeoffs
-
Built AI systems used in production
-
Experience with RAG, vector DBs, or agent frameworks
-
Designed evaluation or monitoring systems
We operate as a dense, senior, high-performance team. We value clarity, speed, craftsmanship, and relentless ownership. We behave like founders - we build, ship, iterate, and hold ourselves to a high technical bar.
If you value excellence, enjoy building real systems, and want to be part of a small team creating something globally impactful, you'll thrive here.