Principal Engineer - Machine Learning

Description

The company builds AI-driven customer and employee engagement platforms. This role is on the AI/ML Engineering team, focused on the core backend services behind an agentic AI platform that powers autonomous AI features across the company's enterprise products.

You will set the architecture and technical direction for these services, and help establish engineering standards, scale the backend, and mentor senior engineers as the agentic capabilities grow to enterprise scale.

Responsibilities

• Design and run the architecture of agent runtime orchestration services covering reasoning, planning, tool calls and low-latency execution.
• Create APIs and SDKs that are easy for developers to use, so internal teams and external partners can build, deploy and manage multi-step agent workflows.
• Build and tune stateful dialog management, shared context and memory services for multi-turn agents that depend on context.
• Set up scalable agent-to-agent communication, coordination patterns and shared memory for distributed multi-agent work.
• Lead the move toward cloud-native, event-driven services built on microservices, a service mesh and event streaming.
• Improve LLM orchestration for speed and cost, including semantic caching, dynamic batching, token monitoring and model routing.
• Direct the build of enterprise RAG pipelines and vector database integrations such as Pinecone, Weaviate and FAISS, plus LangSmith and OpenTelemetry tracing for end-to-end evaluation.
• Set strict standards for unit, integration and load testing, and for tenant isolation through RBAC and multi-tenancy. Mentor engineers to raise the level of the whole team.

Requirements

• 12, 18 years of software engineering and machine learning system development, with a record of designing scalable enterprise backends.
• Strong working knowledge of Java and Python, with production experience using agent frameworks such as LangChain, LangGraph and LangSmith, and workflow engines such as Temporal and Airflow.
• Deep understanding of event-driven architecture, microservices, Kubernetes, Kafka, AWS and mixed database setups such as PostgreSQL and vector databases.
• Proven ability to work through ambiguity, resolve hard architecture bottlenecks, spot technical risk early and coordinate cross-team dependencies to deliver large engineering initiatives.
• Experience turning complex business and AI goals into long-term platform roadmaps and shaping technical decisions across partner engineering teams.
• A record of finding new tools, questioning assumptions and driving continuous technical improvement across an engineering organization.
• Experience with AI planning systems, dialog state tracking or reinforcement learning feedback loops in production.
• Hands-on work with enterprise security frameworks, including SSO, OAuth2, RBAC and multi-tenant data isolation.
• Active contributions to open-source AI or ML projects, or to major LLM and orchestration libraries.
• This is a hybrid role with in-office attendance 3 days a week, Tuesday to Thursday.

Conditions

Hybrid work: in the office 3 days a week, Tuesday to Thursday.

The company is an equal opportunity employer and welcomes candidates of all backgrounds.