AI​/ML Engineer

Overview

AI/ML Engineer to build and maintain the core technical infrastructure that powers its AI agents. The role involves developing backend systems, data pipelines, and integrations essential for deploying and optimizing AI‑driven products, including vector databases, workflow orchestration, and API integrations. The successful candidate will work closely with the Prompt Architect to translate system designs into robust implementations, ensuring efficient, scalable, and reliable AI infrastructure.

None.

None.

Hybrid.

• Design, build, and maintain backend infrastructure for AI agent deployment, including API integrations, data pipelines, and orchestration workflows
• Manage and optimize Retrieval-Augmented Generation (RAG) systems using Pinecone and related knowledge architecture
• Build and maintain n8n automation workflows for agent orchestration and cross‑platform data flows
• Integrate large language models (LLMs) from providers such as Claude and GPT with production systems, handling authentication, error handling, and fallback logic
• Develop integrations with voice platforms (e.g., Eleven Labs), CRMs, communication tools, and third‑party services
• Build the technical foundation for the Builder Agent system, enabling autonomous agent creation pipelines
• Implement fine‑tuning workflows, embedding model management, and evaluation frameworks as needed
• Optimize system performance, latency, and cost efficiency across all infrastructure components
• Collaborate with the Prompt Architect to translate prompt designs into production‑ready technical implementations

• 3+ years of experience in software engineering with a focus on AI/ML infrastructure or backend systems
• Strong proficiency in Python and experience with AI/ML frameworks and libraries
• Hands‑on experience with vector databases (Pinecone, Weaviate, Qdrant, or similar)
• Experience building and consuming RESTful APIs and working with LLM provider APIs (Anthropic, OpenAI)
• Familiarity with workflow automation tools such as n8n or Lang Chain
• Experience with cloud platforms (AWS, GCP, Azure) and containerization (Docker)
• Strong understanding of RAG architectures, embedding models, and knowledge retrieval systems

• Experience with voice AI platforms (Eleven Labs, Deepgram, or similar)
• Background in building multi‑agent systems or agent orchestration frameworks
• Experience with fine‑tuning LLMs or training custom models
• Familiarity with CI/CD pipelines for AI/ML deployment
• Experience with real‑time data processing and streaming architectures