Principal AI Engineer -Enfi
Boston, Massachusetts • Full Time
Posted 8mo ago
Job Location
Boston, Massachusetts
Tech Stack
Remote Work Policy
On-site
Employment Type
Full Time
Categories
Applied AI Engineer
About the job
We are seeking a Principal AI Engineer to provide hands-on technical leadership for complex, production-grade AI systems. This is a deeply technical builder role focused on defining technical direction through coding, system design, and enabling teams to move faster and scale effectively. You will architect and build end-to-end AI systems, including LLM orchestration, retrieval layers, agentic workflows, and structured reasoning systems, while leading the design of multi-agent and tool-calling systems for reliable production operation. The role involves establishing architecture patterns for scalable, cost-aware, and observable AI applications, driving technical decisions across data modeling, AI pipelines, infrastructure, and APIs, and defining best practices for evaluation, monitoring, and governance.
Responsibilities
- Architect and build end-to-end AI systems including LLM orchestration, retrieval layers, agentic workflows, and structured reasoning systems.
- Lead the design of multi-agent and tool-calling systems that operate reliably in production.
- Establish and evolve architecture patterns for scalable, cost-aware, and observable AI applications.
- Drive technical decisions across data modeling, AI pipelines, infrastructure, and APIs.
- Define best practices for evaluation, monitoring, and governance of AI systems in production.
- Mentor senior engineers through design reviews, code reviews, and system-level debugging.
- Translate ambiguous business and domain problems into clear technical strategies.
- Stay ahead of emerging AI techniques and integrate what matters.
Requirements
- 12+ years of software engineering experience, with deep hands-on experience building AI/ML systems in production.
- Strong proficiency in TypeScript, React, Go, Python and modern AI frameworks.
- Extensive experience with LLMs, including RAG, tool use, prompt systems, and agentic architectures.
- Proven ability to design and ship large-scale AI systems that run reliably in real-world environments.
- Strong architectural judgment across data systems, AI models, infrastructure, and application layers.
- Deep understanding of AI failure modes: hallucination, drift, brittleness, latency, and cost blowups.
- Excellent communication skills—able to explain technical tradeoffs to both technical and non-technical audiences.
- Track record of shipping systems end-to-end, not just prototypes or research work.
- Experience with knowledge graph architecture, ontology design, or semantic modeling in complex domains.
- Experience with graph databases, graph query languages, or graph ML techniques.
- Experience with hybrid systems combining structured reasoning with LLM-based approaches.
- Experience with entity resolution, schema alignment, or knowledge fusion at scale.
- Experience with AI systems requiring explainability, auditability, or lineage tracking.
- Experience building AI systems in regulated or high-stakes domains (finance, healthcare, legal, government).
- Experience with MLOps, evaluation infrastructure, or long-running AI services operating at scale.
Benefits
- Owning the technical direction of real AI systems that make it into production
- Solving hard, ambiguous problems where architecture and execution matter equally
- Leading through hands-on building, not layers of process
- Working in an environment that values shipping, learning, and iteration over perfection
- Having the latitude to shape both systems and how teams build them