ML Engineer II

Role description

AI product development

• Design and implement AI features for contact-center use cases, including transcription, summarization, agent assist, analytics, and automation.
• Integrate LLM services, transcription engines, embeddings, vector databases, and RAG pipelines.
• Design prompt strategies, prompt versioning, and evaluation mechanisms for reliable AI behavior.
• Build safe and efficient integrations with external AI providers such as OpenAI, Azure OpenAI, or AWS.

Architecture and software delivery

• Design scalable, modular, observable AI architectures for real-time, high-volume workloads.
• Apply event-driven, asynchronous, and distributed-systems practices; address cost, fault tolerance, latency, throughput, and reliability.
• Build and maintain backend services using Node.js, TypeScript, and NestJS.
• Develop React.js or similar frontend experiences, including AI-assisted workflows and real-time interfaces.
• Contribute to API design, frontend-backend contracts, and system integrations.

Collaboration and engineering quality

• Work with product managers, designers, QA, and engineers from discovery through delivery.
• Translate business and product needs into technical designs and implementation plans; challenge assumptions and propose solutions.
• Write clean, maintainable, tested code; build automated tests for critical and AI-dependent logic.
• Participate in code reviews and architecture discussions, maintain technical documentation, and improve performance, reliability, and developer experience.
• Mentor peers and contribute to engineering practices and standards.

Experience and technical qualifications

• Bachelor’s degree in Computer Science or equivalent practical experience.
• 6–8 years of professional software development experience.
• Strong Node.js, TypeScript, NestJS, and React.js or equivalent frontend framework experience.
• Autonomous feature ownership from concept to production; experience with modular, loosely coupled, event-driven architectures.
• Hands-on experience building AI-powered production features, not only experimentation.
• Knowledge of LLMs, prompt engineering and lifecycle management, RAG, vector search, and knowledge-base ingestion and enrichment.
• Experience integrating OpenAI, Azure OpenAI, AWS Bedrock, or similar AI services.
• Ability to reason about latency, accuracy, cost, and reliability trade-offs in AI systems.

Additional technical qualifications

• Experience with Docker and Kubernetes; familiarity with AWS or Azure cloud-native architectures.
• Experience with message brokers or streaming platforms such as Apache Kafka.
• Strong Git workflows and CI/CD practices; comfort working in Linux environments.
• Knowledge of VoIP, real-time communications, or contact-center platforms; experience with real-time or near-real-time data streams.
• Understanding of observability for distributed and AI-driven systems and awareness of AI governance, security, and privacy for customer data.

Mindset and communication

• Product-oriented, analytical, and critical-thinking approach; favor simple, maintainable solutions over over-engineering.
• Excellent communication and ability to work with distributed teams; fluent English required.
• Constructively challenge ideas, propose alternatives, and stay current with AI and software trends.
• Leadership mindset demonstrated through mentoring, technical guidance, or ownership.