Staff Backend AI Platform Engineer

Freshworks•San Mateo, CA

3h•$225,000 - $278,000•Hybrid

About The Position

We are seeking a Backend AI Platform Engineer to lead the development of core backend services powering our Agentic AI Platform. In this role, you will be the primary technical driver for building reasoning-driven agents, multi-agent orchestration, and outcome-based workflows. You will collaborate with the Principal AI Architect to bridge the gap between high-level design and scalable implementation. You will own the development of high-performance APIs and orchestration runtimes, integrating frameworks like LangChain, LangGraph, and LangSmith. This role is highly hands-on and requires a technical leader who can navigate a fast-paced environment while maintaining high engineering standards.

Requirements

6+ years of backend engineering experience.
1-2+ years of hands-on experience in AI/ML platform development.
Strong programming skills in Java and Python.
Hands-on experience with LangChain, LangGraph, or LangSmith.
Deep understanding of event-driven architectures, microservices, and Kubernetes.
Solid experience with AWS, Terraform, and a mix of relational (PostgreSQL) and Vector databases.
Practical experience with workflow engines like Temporal or Airflow and messaging systems like Kafka.

Nice To Haves

Experience with AI-driven planning systems or dialog state tracking.
Background in enterprise security (RBAC, SSO, OAuth2).
Experience working in a high-growth SaaS or startup environment.
Active contributions to open-source backend or AI frameworks.

Responsibilities

Lead Implementation: Act as the lead engineer for agent runtime orchestration services, focusing on reasoning, planning, and tool invocation.
API & SDK Design: Own the development of robust APIs and SDKs that enable internal and external teams to build and deploy agent workflows.
State & Memory Management: Build and optimize stateful dialog management and memory services for multi-turn, context-aware agents.
Agent Communication: Implement multi-agent communication (A2A) protocols and shared context systems.
Microservices Leadership: Execute the transition to cloud-native, event-driven backend services using microservices or service mesh architectures.
Workflow Design: Build and manage task scheduling and long-running operations using tools like Temporal or Airflow.
Performance Optimization: Optimize LLM orchestration for performance and cost through caching, batching, and token monitoring.
Data Pipeline Ownership: Implement and maintain RAG pipelines and integrations with vector databases (e.g., Pinecone, Weaviate, FAISS).
Telemetry Integration: Ensure all backend services support LangSmith-based evaluation and comprehensive observability.
Tenant Isolation: Implement RBAC, API authentication, and multi-tenant isolation logic.
Engineering Excellence: Set the standard for automated testing (unit, integration, load) and implement OpenTelemetry for full system visibility.
Mentorship: Provide technical guidance and code reviews for more junior backend engineers on the team.