Staff Engineer - Machine Learning
Core
Lead development of core backend services, reasoning-driven agents, multi-agent orchestration, and outcome-based workflows for an Agentic AI Platform.
Role type
Staff Machine Learning Engineer (Backend & Orchestration)
Builds
Agent runtime orchestration services, high-performance APIs/SDKs, stateful dialog management, multi-agent communication protocols, cloud-native microservices, and RAG pipelines.
Domain
Artificial Intelligence / Machine Learning / Distributed Systems / Cloud Infrastructure
Deliverable
production ML models | product features | infrastructure
Required skills
Java, Python, LangChain, LangGraph, LangSmith, Microservices, Kubernetes, AWS, Terraform, PostgreSQL, Vector Databases, Workflow Engines (Temporal/Airflow), Kafka, RBAC, OpenTelemetry
Preferred skills
AI-driven planning systems, Dialog state tracking, Enterprise security (SSO/OAuth2), High-growth SaaS/Startup experience, Open-source contributions
Technologies
LangChain, LangGraph, LangSmith, Pinecone, Weaviate, FAISS, Temporal, Airflow, Kafka, Kubernetes, AWS, Terraform, PostgreSQL
Responsibilities
Lead implementation of agent runtime orchestration services; Design and develop robust APIs and SDKs for agent workflows; Build and optimize stateful dialog management and memory services; Implement multi-agent communication protocols; Execute transition to cloud-native event-driven microservices; Optimize LLM orchestration for performance and cost; Implement RAG pipelines and vector database integrations; Enforce security standards (RBAC, tenant isolation) and engineering excellence (testing, observability); Mentor junior backend engineers.
Seniority
Staff, hands-on technical leader with mentorship responsibilities