Principal AI Engineer

Responsibilities

• System Architecture: Design and maintain robust backend systems, microservices, and APIs using Python, focusing on high-level system design and architecture.
• Distributed Infrastructure: Architect and deploy distributed infrastructure for high-throughput AI workloads and agent coordination.
• Model Integration: Collaborate with ML engineers to integrate trained models into scalable production environments.
• Inference Pipelines: Build and maintain real-time and batch inference pipelines for AI-driven tasks.
• MLOps & DevOps: Contribute to CI/CD automation, observability, monitoring, and autoscaling for AI services.
• Performance Optimization: Ensure high availability, security, and performance across all backend deployments and model-serving infrastructure.

Requirements

• Strong professional experience with Python in production-grade systems. Deep understanding of system design, distributed systems, Python asyncio models, and network programming.
• Proven experience building AI Agents using frameworks like LangChain or OpenCLAW.
• Hands-on experience with MCP (Model Context Protocol) servers: understanding what they are, how to build them to provide tools/data to LLMs, and how they facilitate agentic communication.
• Expertise in Vector Databases (e.g., FAISS, Pinecone, Weaviate) for building Knowledge Bases and RAG (Retrieval-Augmented Generation) pipelines.
• Familiarity with ML frameworks such as PyTorch, TensorFlow, or JAX. Experience with model-serving platforms like Triton Inference Server, TorchServe, ONNX Runtime, or Ray Serve. Proficiency in containerization and orchestration using Docker and Kubernetes.
• Experience with SQL/NoSQL databases, caching systems (Redis), and message queues like Kafka or RabbitMQ.