Expert AI Engineer
Role details
Job location
Tech stack
Job description
The Expert AI Engineer owns complex technical work within GenAI and AI platform services, designing and optimizing components of retrieval pipelines, inference systems, and evaluation frameworks. Applies strong debugging, performance engineering, and architectural judgment to improve system reliability and model grounding, while guiding less-experienced team members and influencing team-level technical decisions.
GenAI & AI Platform Development
- Design, implement, and optimize RAG pipelines, embeddings workflows, and LLM integration patterns.
- Contribute to scalable, low-latency inference architecture across real-time and batch pipelines supporting document processing, portfolio insights, and decision-support use cases.
- Design ingestion, transformation, and indexing pipelines for vector stores and hybrid retrieval, including data curation processes and retrieval corpora in partnership with domain experts.
- Improve pipeline performance, reliability, integration quality, and cost-efficiency across GenAI workflows.
- Design and maintain prompt templates, orchestration flows, and model configurations, establishing patterns for versioning, rollback, and auditability.
- Implement secure-by-design principles and contribute to responsible AI guidelines.
- Design and implement guardrail patterns (e.g., safety classifiers, content filters, policy checks) to mitigate harmful or non-compliant outputs.
AI Evaluation & Quality Engineering
- Design evaluation frameworks, datasets, and metrics to measure grounding, factuality, consistency, safety, and overall model quality.
- Build automated test harnesses and evaluation pipelines to support model iteration and validation.
- Analyze evaluation results and translate findings into actionable improvements to models and workflows.
- Apply grounding strategies and structured response patterns to reduce hallucinations and improve reliability.
Software Engineering & System Design
- Lead the design and implementation of core GenAI system components and services.
- Participate in architectural discussions and propose improvements within the product area.
- Write modular, reusable, and maintainable code adopted across the team.
- Conduct code reviews, design reviews, and performance troubleshooting to ensure high-quality, optimized systems.
- Mentor less-experienced engineers on coding standards, testing practices, and system design.
Requirements
Do you have experience in Validation design?, * Strong software engineering background with hands-on experience in AI/ML or LLM-based systems.
- Deep experience with RAG architectures, embeddings pipelines, retrieval workflows, and LLM orchestration.
- Experience designing evaluation frameworks, datasets, and offline testing approaches.
- Proficiency with cloud-native architectures, microservices, and containerization.
- Demonstrated commitment to high-quality code, testing, documentation, and system reliability.
- Proven ability to mentor others and influence technical decisions within a team., * Typically requires 6+ years of professional experience in AI/ML engineering, including ownership of model development and system integration.
Benefits & conditions
Pulled from the full job description
- Employee stock purchase plan
- 401(k)
- Wellness program, We offer a competitive compensation and benefits package, opportunities for career growth, an employee stock purchase plan, 401(k), generous time off and flexible work/life balance, company-matched retirement packages, an employee wellness program, and an awards and recognition program - all in a creative, fast-growing, and innovative company.