Senior AI Engineer – Agentic Systems & Data Engineering

Location: Remote

Type: Full-time | Core AI Engineering Team | Senior Individual Contributor / Technical Lead

About Taiyo.AI

Taiyo.AI is building a living world model of the built economy—an intelligence platform connecting infrastructure projects, construction, energy, investment, companies, procurement, and real-world risks.

Our proprietary data ecosystem spans millions of projects, tens of millions of tenders, and thousands of sources worldwide. We're turning this fragmented information into structured, continuously evolving intelligence that enterprises can interrogate through advanced AI agents and decision-making workflows.

We're building at the frontier of applied AI, large-scale data engineering, and domain-specific intelligence systems. Our challenge isn't simply making LLMs answer questions. It's building systems that know what is happening in the real world, distinguish evidence from inference, deal intelligently with uncertainty, and improve as new information arrives.

The Role

We're looking for an exceptional, hands-on AI Engineer who can help architect, build, and scale the next generation of Taiyo's intelligence infrastructure.

You'll work across advanced Python engineering, agentic AI orchestration, AI-powered data enrichment, entity intelligence, retrieval systems, and large-scale data pipelines.

We're a small team with large technical ambitions. You'll have significant ownership, work directly with the founders and engineering team, and be expected to move quickly from architectural thinking to working production systems.

This is a builder's role, not a research-only position or a prompt engineering job.

What You'll Build

• Advanced AI Agents & Orchestration
• Design and develop sophisticated agentic workflows using LLMs, tools, APIs, retrieval, and structured reasoning.
• Build robust multi-step and multi-agent execution systems with clear state management, error handling, and observability.
• Develop orchestration that integrates multiple models, proprietary data, external information, and enterprise workflows.
• Improve agent reliability, grounding, latency, evaluation, and inference economics.
• Experiment rapidly with emerging AI architectures while maintaining production engineering discipline.

2. AI-Native Data Engineering & World Models

• Build scalable pipelines for ingesting, processing, normalizing, and enriching large volumes of structured and unstructured data.
• Develop AI-driven extraction, classification, entity resolution, deduplication, and information reconciliation systems.
• Help create persistent, interconnected representations of projects, organizations, assets, locations, events, relationships, and their evolution over time.
• Develop reliable methods for integrating multiple conflicting or incomplete sources into coherent, structured intelligence.
• Build scalable enrichment systems for future infrastructure projects, project status, timelines, financing, procurement, delivery methods, risks, and other domain-specific attributes.
• Contribute to flexible data schemas, taxonomies, knowledge graphs, and emerging industry data standards.

3. Data Reliability, Provenance & AI Evaluation

• Engineer systems that distinguish verified facts, sourced estimates, model inferences, and genuinely unknown information.
• Build source-level provenance, evidence linking, confidence assessment, temporal tracking, and structured uncertainty management.
• Design automated validation, quality monitoring, and evaluation frameworks for AI-generated data and agent outputs.
• Develop mechanisms to detect contradictions, stale information, hallucinations, and inconsistent entity relationships.
• Create measurable improvements in data accuracy, completeness, freshness, and traceability.

4. Production AI Infrastructure & Backend Systems

• Build production-grade Python services, APIs, asynchronous workflows, and distributed processing infrastructure.
• Work with cloud services, databases, search indexes, vector retrieval, queues, and scalable data architectures.
• Improve the reliability, performance, monitoring, and cost efficiency of AI and data systems.
• Own features end to end, including design, implementation, testing, deployment, and continuous improvement.

What We're Looking For

• Strong production Python engineering skills, ideally 4–7+ years of relevant experience.
• Demonstrated experience building complex AI applications, LLM orchestration systems, or agentic workflows.
• Strong foundations in data engineering, SQL, data modeling, APIs, and distributed or asynchronous systems.
• Experience with structured data extraction, retrieval, enrichment pipelines, or large-scale information processing.
• Familiarity with cloud infrastructure (AWS preferred), Docker, production deployment, and engineering observability.
• Sound understanding of LLM limitations, grounding, evaluations, reliability, and production failure modes.
• Ability to write excellent code, think architecturally, debug difficult problems, and ship quickly.

Especially Valuable

• LangGraph, LangChain, LlamaIndex, or custom agent orchestration architectures.
• Knowledge graphs, entity resolution, temporal data modeling, and semantic data systems.
• Apache Spark, Ray, Airflow, Dagster, or comparable data processing technologies.
• FastAPI, Pydantic, PostgreSQL, OpenSearch/Elasticsearch, vector databases, or graph databases.
• LLM evaluation, tracing, experimentation, model routing, and cost optimization.
• Experience with Langfuse or similar AI observability tools.
• Experience developing high-reliability AI enrichment pipelines using real-world, incomplete, or contradictory datasets.

We care more about demonstrated engineering depth and exceptional execution than specific frameworks or academic credentials.

Who Thrives Here

You have built serious systems, not just demos.

You are comfortable working at the intersection of AI research developments and pragmatic production engineering.

You think deeply about architecture, correctness, and failure modes, but you're also fast, resourceful, and willing to get your hands dirty.

You enjoy ambiguous problems, take ownership without waiting for instructions, and can move from experimentation to scalable implementation.

You're intellectually curious, ambitious, and excited by the challenge of building a foundational intelligence platform for a massive global industry.

Why Join Taiyo.AI?

You'll help solve challenging problems at the frontier of agentic AI and real-world intelligence, working with one of the richest emerging data ecosystems focused on the physical economy.

You'll have the opportunity to shape the architecture of a living world model, build new AI capabilities used by major enterprises, and grow into a technical leadership role as the platform scales.

You'll join a small team where exceptional engineers have real influence, meaningful ownership, and the freedom to build.