Sr. Applied AI Engineer

Vantaca + HOAi • Wilmington, NC

4d • Remote

About The Position

Vantaca is building a world-class Applied AI practice within its Applied AI team. This role requires an engineer who can ship production-grade ML and LLM systems for the Implementation and Client Enablement teams. This is not a prompt engineering role or an AI exploration sandbox. The engineer will build systems that are evaluated, deployed, and observed, owning the gap between an "interesting model" and a "thing that reliably runs in production." The role involves partnering with Implementation PMs, Solution Consultants, and Client Enablement Specialists to identify high-leverage problems and ship tooling that removes friction across the client lifecycle. The work is high-trust and high-autonomy, with the engineer owning their problem space end to end.

Requirements

• Production experience shipping both classical ML and LLM systems, with strong opinions on when to use each.
• An eval-first mindset; building measurement before the model.
• Fluency in a data warehouse environment, including SQL and time-aware feature engineering with leakage discipline.
• Production experience with model degradation, label loop bias, and LLM provider regressions.
• Cost intuition to napkin-math the unit economics of an LLM workflow before committing.
• Ability to scope work in partnership with non-technical stakeholders, translating their pain into a buildable system.
• Comfort distinguishing the business metric from the model metric and arguing for the right one.
• Use AI tools (Claude, Cursor, Claude Code, or equivalent) as a core part of your daily workflow.
• Python proficiency as the primary build language for automation and scripting.
• Full-stack range: comfortable building APIs, automations, integrations, and lightweight UIs without needing a separate front-end resource.
• SQL and data fluency: ability to work regularly in the data warehouse and understand/act on operational data directly.
• API integration experience: REST, webhooks, OAuth.
• RAG and retrieval system experience: chunking, embedding strategies, retrieval quality, hallucination mitigation.
• Prompt and context engineering: understanding context boundaries and strategies for persistence vs. retrieval.
• DevOps fundamentals: CI/CD, Infrastructure as Code, containerization; ability to ship and maintain built systems.
• AI/ML background is required; CS or AI/ML academic track preferred.
• Spec-first by default: writing detailed intent documents before building.
• Bias toward shipping: preferring a v1 in two weeks over architecting a v3 for two months.
• Product sense for non-technical users: translating operational pain into a scoped technical solution.
• Comfortable operating as the sole AI engineer in a domain.
• Builder, not buyer: building internal tooling rather than stitching together SaaS products.
• Security-aware: asking about access scoping and data classification before building.
• Comfortable with ambiguity and shifting requirements, orienting toward the outcome.
• Strong written communicator: documenting intent and leaving clear records of built systems.

Responsibilities

• Design and ship ML and LLM systems spanning supervised models that predict and rank, retrieval and generation systems that draft and summarize, and agentic workflows that act on internal data.
• Build evaluation infrastructure alongside every system, defining success criteria before writing code, measuring system performance, and catching regressions before users do.
• Architect RAG, retrieval, and context engineering patterns that allow LLMs to operate reliably on internal knowledge and production data.
• Reason rigorously about modeling choices, including label definition, leakage, time-aware splits, calibration, precision-at-k vs AUC, and when a heuristic baseline outperforms a model.
• Work directly in Databricks and Unity Catalog, understanding operational data, writing SQL, and building systems that act on it.
• Own deployment and monitoring for all shipped systems, including feature drift, outcome tracking, LLM eval regression, retraining cadence, and rollback paths.
• Treat data governance and access scoping as design constraints.
• Maintain versioned, traceable LLM workflows, including reusable prompts and context patterns.

Benefits

• Medical
• Dental
• Vision
• Unlimited PTO (with a requirement for employees to take a minimum of one continuous week per year)
• 401K with Company Match
• Great parental leave benefits
• Ongoing industry and professional development trainings

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed