Applied AI Engineer

MeltPlan | Planning Engine for the Built Environment

MeltPlan is building the “planning engine” for the $14 Tn construction industry, an AI system designed specifically to optimize decisions before construction begins. While design software optimizes use and aesthetics and construction software optimizes execution and control, MeltPlan is building the missing layer - software that optimizes decisions and tradeoffs upstream, before scope is locked, procurement begins, and change orders become inevitable. MeltPlan’s long-term goal is to help teams make construction “boring” by making planning more intense: surfacing constraints and tradeoffs early, aligning stakeholders before plans are frozen, and reducing the need for late-stage redlines, rework, and change orders.

MeltPlan is founded by operators who have built at scale. Kanav previously co-founded Innovaccer, a $3Bn healthtech company focused on making US healthcare more affordable and accessible. He’s now applying that systems-level thinking to construction.He’s joined by Tanmaya Kala, former Project Executive at DPR Construction, who led large commercial, healthcare, and life sciences projects. We combine deep tech scale with real construction execution.

What This Role Really Is

This is not an “AI feature engineer.” This is a systems engineer for AI.

Anyone can call an LLM API. We need someone who can engineer intelligent systems that are:

• Structured (DAG-based workflows, not spaghetti prompts)
• Observable (traceable, debuggable, measurable)
• Evaluated (offline + online evals, regression detection)
• Economical (token usage, latency, cost-aware architecture)
• Production-grade (reliable under real-world noise)

You won’t just prompt models.
You’ll design AI pipelines that behave predictably in unpredictable environments.

What You’ll Do

• Architect AI workflows using DAG-based orchestration
• Design structured prompt systems and agent flows
• Build evaluation frameworks (automated + human-in-the-loop)
• Implement observability: logging, tracing, failure analysis
• Optimize token usage, latency, and cost across workflows
• Design retrieval systems (embeddings, chunking, ranking)
• Create guardrails and structured outputs for reliability
• Continuously improve model performance with measurable metrics

You’ll turn probabilistic systems into dependable infrastructure.

What We’re Looking For

• Strong backend or systems engineering fundamentals
• Experience building production AI systems (not demos)
• Understanding of:
• Prompt design and structured outputs
• RAG systems
  Evaluation pipelines
• Workflow orchestration
• Monitoring + logging for LLM systems
• Comfort debugging non-deterministic behavior
• Ability to think in tradeoffs (latency vs cost vs quality)

Bonus if you’ve:

• Built multi-step agent systems
• Designed internal eval harnesses
• Optimized token economics at scale
• Worked in messy real-world data environments

Why MeltPlan

• Massive industry, real-world impact
• High ownership from day one
• Small team, zero bureaucracy
• Competitive comp + meaningful equity

How to Apply

Send us:

• Your GitHub
• Links to products you’ve shipped
• A short note on something you built that you’re proud of

We value builders. Show us what you’ve made.