AI Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Contribute to the strategic technical direction for AI-enabled systems alongside senior engineers and the architecture team.

• Engage in design reviews for AI-related features and integrate feedback from senior engineers and architects.

• Develop production-quality Python services, pipelines, and integrations that leverage LLMs and retrieval methods to address internal and product challenges.

• Incorporate LLM APIs into existing systems, adhering to established guidelines on model selection, cost considerations, and failure management.

• Ensure that AI functionalities respect schema-per-tenant and PHI-boundary patterns within the multi-tenant architecture.

• Collaborate with the data and analytics team on retrieval- and LLM-enhanced features for the lakehouse and analytics layer, including embedding, chunking, retrieval evaluation, semantic search, summarization, anomaly narration, and contextual guidance.

• Contribute to prompt libraries, evaluation frameworks, reference implementations, and reusable components; assist in refining standards for model selection, evaluation, testing, observability, and cost control.

• Assess emerging AI tools and provide insights on build-versus-buy strategies.

• Develop AI implementations that comply with HIPAA, SOC 2, and NIST standards, including PHI management, data residency, audit logging, BAA coverage, prompt-injection defenses, LLM DLP, model access governance, and secrets management.

• Maintain comprehensive documentation of AI systems, data flows, and risk assessments for audit and compliance purposes.

• Work collaboratively with engineering, product, customer success, security, data, and operations teams to identify opportunities for automation, translate them into technical plans, and contribute to the customer-facing AI roadmap.

• Participate in operational quality and on-call rotations, which include incident response, post-incident reviews, observability, and feedback loops to enhance retrieval quality, prompt behavior, and agent reliability.

• Monitor production AI costs, quality, and adoption metrics, reporting outcomes to the manager, architecture team, and team leads.

• Implement enterprise AI-integration best practices and share knowledge with colleagues.

⛳️ Requirements

• 3–5 years of software engineering experience, with a minimum of one year focused on AI- or ML-driven systems, including contributions to at least one LLM-backed system in production.

• Proficient understanding of programmatic LLM orchestration, evaluation frameworks, and systems utilizing agents and tools, with experience in securely connecting enterprise APIs to agentic systems.

• Strong Python programming skills for developing production services, data pipelines, and integration tasks.

• Experience in building retrieval-augmented systems, including familiarity with enterprise data architectures like Databricks and Azure/AWS.

• Excellent written and verbal communication skills.

• Knowledge of CI/CD, infrastructure-as-code, and MLOps practices applicable to AI/ML systems.

• Familiarity with generative AI tools such as Claude and Copilot to enhance productivity and deliver high-quality results.

• Production experience in a regulated industry, with practical knowledge of HIPAA, SOC 2, or NIST, and experience with multi-tenant SaaS data isolation and identity/access patterns for B2B platforms (preferred).

• Bachelor's or master's degree in Computer Science, Engineering, Data Science, or a related field.

🏝️ Benefits

• Remote position

• Equal Opportunity Employer