AI Engineer – Full Stack AI Backend & Infrastructure

We are looking for an AI Engineer to own the complete AI backend stack end-to-end, from agent architecture and model integration to deployment, monitoring, and continuous improvement.

The role involves designing and building multi-agent AI systems, retrieval pipelines, scalable backend services, and production-ready AI infrastructure. You will work across AI engineering, backend engineering, and DevOps to architect systems, ship production code, debug production issues, and make cost, quality, and latency trade-offs.

The ideal candidate should have strong backend development experience, hands-on experience building and deploying LLM and AI systems in production, and the ability to work across AI, backend, and infrastructure.

• 4+ years of professional experience.
• Strong backend development experience, with Python preferred.
• Hands-on experience with LLMs and AI systems in production.
• Experience with vector databases and retrieval systems.
• Understanding of distributed systems and asynchronous processing.
• Familiarity with cloud platforms such as AWS, GCP, or Azure.
• Experience working across AI, backend, and infrastructure.
• Strong ownership mindset and ability to take responsibility for production systems.
• Practical problem-solving approach with a focus on shipping production-ready systems.

• Design and scale multi-agent orchestration systems with 10+ specialized agents.
• Implement parallel execution using fan-out/fan-in, conditional routing, and shared state handling.
• Build domain-specific agents with tailored retrieval, prompts, tools, and fallback strategies.
• Develop graph-based routing logic for dynamic task handling.
• Manage multi-model and multi-provider LLM architectures.
• Select models based on cost, latency, and accuracy trade-offs.
• Build and refine prompt systems, including few-shot and domain-tuned approaches.
• Optimize token usage, latency, and response quality.
• Build hybrid retrieval pipelines using vector search, keyword search, and metadata filtering.
• Optimize chunking, indexing, embeddings, and re-ranking strategies.
• Develop scalable backend services for AI pipelines.
• Implement streaming responses and asynchronous processing.
• Deploy and manage services using cloud infrastructure.
• Maintain CI/CD pipelines and production environments.
• Build monitoring systems for latency, errors, and model performance.
• Track hallucinations, failure cases, and edge scenarios.
• Implement fallback systems and reliability layers.
• Optimize inference costs and continuously improve system efficiency