AI Engineer
Selfic AI
Published Date: • Remote
Description
As an experienced AI Engineer with at least five years in the field, you will be responsible for building robust data ingestion and document processing pipelines, optimizing embeddings and retrieval mechanisms, and conducting comprehensive evaluations of AI model accuracy, latency, cost-efficiency, and reliability. You will also handle secure credential management and implement monitoring procedures to support operational excellence. Furthermore, your role involves supporting client demonstrations, acceptance testing, and production launches, as well as maintaining detailed technical documentation and resolving any issues that arise. Your ability to identify technical risks and communicate them effectively to senior leadership will be critical to the success of projects and ongoing innovation at Selfic AI.
Responsibilities
- Collaborate with Functional Design Engineers to review requirements, assess technical feasibility, estimate effort, and identify dependencies for AI projects.
- Lead the development of AI agents, large language model workflows, and retrieval-augmented generation solutions tailored to business use cases.
- Design and build backend services and APIs that integrate seamlessly with client applications, databases, and approved data sources.
- Implement data ingestion pipelines, advanced document processing methods, and embedding techniques, ensuring compliance with client data permissions and security policies.
- Evaluate AI model accuracy, system reliability, response latency, and cost of usage; systematically test failure scenarios and enhance solution robustness.
- Apply rigorous access control measures, secure credential handling, and client data protection protocols throughout development and deployment processes.
- Deploy AI solutions across cloud platforms, on-premises environments, or hybrid infrastructures with a focus on scalability, security, and performance monitoring.
- Establish operational support procedures including monitoring, logging, and alerting to ensure continuous service availability and rapid incident response.
- Provide technical expertise during client demonstrations, acceptance testing phases, and live deployments; promptly address and resolve defects or issues.
- Maintain comprehensive technical documentation including architecture designs, workflows, APIs, and deployment procedures to facilitate knowledge sharing and compliance.
- Manage and mentor a team of 10 AI engineers, fostering collaboration, skill development, and adherence to project timelines and quality standards.
- Identify potential technical risks, blockers, and challenges during the project lifecycle and escalate them promptly to the Chief Technology Officer.
- Ensure adherence to approved architectural frameworks, quality assurance policies, and release management protocols throughout project execution.
Experience
5 Years
Apply By
Required Skills
- AI Model Evaluation and Deployment
- Large Language Models
- Backend Service Development
- API Integration
- Data Ingestion
- Document Processing
- Embedding techniques
- Cloud Deployment
- On-premises deployment
- Security and Access Control
Nice to Have Skills
- Hybrid Environment Management
- Monitoring and Operational Support
- Technical Documentation
- Team Management