Lead AI Systems Engineer (LLM + Infrastructure)

About the role

We’re hiring a senior, hands-on engineer to help own and evolve the core AI systems behind Melzi.

Melzi is not an idea-stage startup. The platform has been under active development for over 3 years, with more than full-time founder effort behind much of that journey. We have already launched 2 products, and the main platform is live in closed beta. The foundation is built. What comes next is extending, scaling, and strengthening a system that is already in production.

This role is for someone who can work directly on the core LLM and infrastructure stack, improve what already exists, and help take the system to the next level.

This is a highly hands-on engineering role. It is not a management-only role, and it is not a co-founder role.

Over time, this role will also help shape engineering direction, standards, and early team growth as we expand.

What you’ll do

• Own and evolve core LLM pipelines and orchestration systems
• Work on advanced retrieval and context systems (RAG, training, hybrid approaches)
• Enhance system performance, efficiency, and scalability
• Build and extend integrations across external tools and services
• Help with multi-tenant scale and production growth
• Contribute to architecture decisions and long-term system design
• Work directly on production systems with real usage
• Contribute code, solve real system problems, and help set a strong engineering standard as the team grows
• Provide technical guidance and help shape how future engineers are on-boarded and operate

What we’re looking for

• Strong experience building and shipping production LLM systems
• Deep understanding of training and RAG architectures, prompt orchestration, retrieval pipelines, and LLM orchestration
• Strong backend engineering skills in Python (Node.js addition a plus)
• Experience with scalable distributed systems and cloud infrastructure
• Comfortable operating in an early-stage environment with high ownership and low bureaucracy
• Able to work independently, move quickly, and make sound engineering decisions without excessive overhead
• Strong communication skills and ability to influence technical direction through execution
• A mindset oriented toward building, ownership, and raising the bar for engineering quality

Nice to have

• Experience with vector databases such as Qdrant, Pinecone, or similar
• Experience with hybrid retrieval and search relevance tuning
• Experience with async pipelines, ingestion systems, high-throughput and AI workflow orchestration
• Experience working on multi-tenant SaaS systems
• Familiarity with frameworks such as LlamaIndex, LangChain, or similar tooling

What this role is not

• Not a pure people-management position
• Not a “strategy only” architecture role
• Not a co-founder or title-seeking executive track
• Not a fit for someone whose LLM experience is mostly experimental, advisory, or superficial

Who this is a strong fit for

This role is a strong fit for someone who wants to join an early but real platform, work on meaningful AI systems already in motion, and help scale something that has moved beyond concept and into product reality.

It is especially well-suited for engineers who want to lead through building, take ownership of critical systems, and grow into a broader leadership role as the team expands.

Work authorization

Applicants must be based in the United States and must already have valid US work authorization. We are not able to provide visa sponsorship now or in the future for this role.

Compensation

Early-stage compensation structure with equity and leadership upside. We’re transparent about stage and expectations from the start.

About Melzi

Melzi is building a human-centered AI platform for personalized assistants and real-world workflows. We focus on practical systems, strong privacy principles, and products that help people get real outcomes. Multiple products are already live, and the broader platform is actively progressing toward scale.