Senior Backend AI Engineer

We are seeking an AI Engineer to design, build, and deploy AI-powered capabilities within our product.

This role focuses on integrating machine learning models and large language models (LLMs) into scalable software systems and delivering reliable AI-driven features to production.

The AI Engineer works at the intersection of software engineering, AI systems, and infrastructure.

transforming AI technologies into practical applications.

Responsibilities:

• Build applications powered by machine learning and large language models (LLMs).
• Implement capabilities such as intelligent assistants, semantic search, automation, and recommendation systems.
• Integrate AI functionality into backend services and product workflows.
• Design and implement retrieval pipelines, embedding pipelines, and inference workflows.
• Build Retrieval-Augmented Generation (RAG) systems and AI-driven services.
• Create scalable AI architectures capable of handling production workloads.
• Package and deploy AI models as production services.
• Optimize inference performance, scalability, and latency.
• Monitor AI services to ensure reliability and performance.
• Develop backend services and APIs that expose AI capabilities.
• Integrate AI systems with databases, internal services, and external APIs.
• Contribute to system architecture and microservices design.
• Implement logging, metrics, and observability for AI systems.
• Track model performance and system reliability in production environments.
• Work closely with product managers, engineers, and data scientists.

Requirements:

• 5+ years of programming skills in one or more modern languages (such as Python, Java, Go, or similar).
• Experience building backend services and APIs.
• Experience integrating machine learning models or LLMs into applications.
• Understanding of microservices architecture and distributed systems.
• Experience with Docker and containerized applications.
• Familiarity with Kubernetes or cloud infrastructure.
• Experience working with databases and data processing pipelines.

Preferred Qualifications:

• Experience building LLM-based applications.
• Experience with RAG architectures and embeddings.
• Experience with vector databases or semantic search systems.
• Familiarity with model serving frameworks or inference platforms.
• Experience working in production AI environments.

Strong Advantage:

• Experience working with local or self-hosted AI models (e.g., Llama, Mistral, or similar).
• Experience deploying AI models in on-premise or private cloud environments.
• Familiarity with running LLM inference locally using frameworks such as Ollama, vLLM, or Hugging Face Transformers.
• Experience optimizing models for GPU/CPU inference and resource-constrained environments.