Head Of Engineering / Tech Lead

ABOUT BELLAGENT Bellagent is an enterprise-level AI agent platform built to automate everyday business operations with zero-touch integrations that connect instantly to more than 1,300 applications. Launched in 2025 by Proactifi Inc., and headquartered in Chicago, the platform is built for practicality with industry-leading compliance and security standards, the platform enables organizations to deploy AI agents without friction from day one. Bellagent’s mission to make powerful, enterprise-level AI practical and accessible is helping businesses of all sizes operate smarter, serve customers better and compete in an AI-driven economy. ROLE OVERVIEW We are looking for a Tech Lead / Head of Engineering to own the technical direction of Bellagent.ai. This is a hands-on, backend-focused leadership role for someone who has scaled real systems, understands long-term architectural tradeoffs, and is excited to grow into an engineering leader while continuing to build. You will be responsible for system design, architecture decisions, execution quality, and technical standards while actively coding and mentoring a globally distributed engineering team. RESPONSIBILITIES Architecture & System Design Own long-term technical architecture and system design decisions Lead the evolution of the platform from monolithic foundations to modular, service-oriented and microservice architectures Design scalable, maintainable systems that balance velocity with reliability Backend & Platform Engineering Lead backend development across AI infrastructure, integrations, and core platform services Ensure systems are observable, secure, and production-grade Design and implement systems supporting: Modular, agentic AI workflows MCP servers and context memory protocols (bonus) Vector databases and retrieval pipelines LLM orchestration, tool calling, and agent execution AI & Agentic Systems Build and scale LLM-based systems and agentic architectures Collaborate closely on memory, context management, and retrieval strategies Hands-on experience with: Pinecone (or equivalent vector databases) LangChain and LangGraph Modular AI pipelines and orchestration frameworks Execution and Engineering Operations Set engineering standards, best practices, and code quality expectations Make pragmatic operational tradeoffs for web and SaaS applications Partner closely with Product (TPM/Product Owner) to translate roadmap into shipped systems Lead spring execution, reviews, and technical planning Leadership & Team Growth Mentor engineers and help scale a high-performing, globally distributed team Lead by example through hands-on contribution and clear technical direction Grow into the Head of Engineering role as the company scales, owning hiring, structure, and technical culture Requirements WHAT WE'RE LOOKING FOR Background & Experience Computer Science degree (Required) 7+ years of professional engineering experience Experience scaling systems from monoliths to modular or microservice architectures Proven ability to make and defend long-term architecture decisions Technical Depth Strong backend focus with full-stack awareness Deep understanding of: System design and distributed systems Object-oriented design principles and clean architecture Web and SaaS operational tradeoffs (latency, reliability, scaling cost) Hands-on experience with: Python LLM-based engineering and AI systems Vector databases (Pinecone or similar) LangChain, LangGraph, or comparable frameworks Bonus: MCP Engineering (Claude or similar ecosystems) Familiarity with deep neural networks and ML fundamentals Familiarity with Next.js and React for full-stack collaboration Operating Style Builder-first mindset with strong ownership and accountability Comfortable operating in ambiguity and early-stage environments Strong written and verbal communication skills Bias towards pragmatic solutions that ship and scale