Backend Engineer

About the role

We're looking for a Backend Engineer to build the core infrastructure that powers HyperOrbit's autonomous AI agents. You'll design and maintain scalable systems that process millions of customer conversations, build our proprietary customer knowledge graph, and ensure our platform is fast, reliable, and secure as we grow.

This role is critical to our mission: enabling AI agents to work autonomously 24/7, converting scattered customer feedback into actionable business intelligence.

What You'll Build

Agent Infrastructure

• Design multi-agent orchestration systems that coordinate Voice of Customer and Competitive Intelligence agents

• Build real-time data pipelines processing millions of customer interactions daily

• Create agent decision-making engines with confidence scoring and action triggering

• Develop agent learning systems that improve accuracy over time

Customer Knowledge Graph

• Build and maintain our proprietary knowledge graph connecting customers, feedback, features, competitors, and outcomes

• Design graph schemas for complex relationship mapping (customer → feedback → feature request → competitive gap → product decision)

• Implement graph traversal algorithms for insight generation and pattern recognition

• Optimize graph queries for real-time agent decision-making

• Create entity resolution systems for duplicate detection across data sources

Data Pipeline & Processing

• Build scalable ingestion pipelines for 50+ integration sources (Zendesk, Gong, Salesforce, G2, etc.)

• Design real-time streaming architectures for immediate feedback processing

• Implement NLP preprocessing pipelines for sentiment, entity extraction, and categorization

• Create data quality systems ensuring accuracy and consistency

API & Integration Layer

• Design RESTful APIs for agent configuration, insights delivery, and action triggering

• Build webhook systems for bi-directional updates with customer tools (Jira, Slack, Linear)

• Create authentication and authorization systems (OAuth 2.0, SSO/SAML)

• Develop rate limiting and API versioning strategies

Responsibilities

Core Engineering

• Design, develop, and maintain APIs and backend services powering autonomous agents

• Build scalable infrastructure supporting millions of customer conversations processed daily

• Optimize system performance for real-time insight generation and action triggering

• Implement security best practices and data protection protocols (SOC 2, GDPR, CCPA)

• Monitor and troubleshoot backend systems to ensure 99.9% uptime

Knowledge Graph Development

• Design and implement customer knowledge graph architecture

• Build graph-based recommendation and pattern recognition systems

• Optimize graph database performance for complex queries

• Create graph visualization APIs for frontend consumption

• Implement graph versioning and historical analysis capabilities

Agent Orchestration

• Build systems coordinating multiple specialized agents (VOC, CIA)

• Create agent communication protocols for cross-validation and learning

• Implement agent priority systems and resource allocation

• Design agent performance monitoring and optimization frameworks

Data & ML Infrastructure

• Collaborate with AI/ML team on model serving and inference optimization

• Build feature engineering pipelines for agent decision models

• Create A/B testing infrastructure for agent improvements

• Implement model versioning and rollback capabilities

Cross-Functional Collaboration

• Work with product and frontend teams to deliver seamless user experiences

• Partner with AI/ML engineers on agent intelligence improvements

• Collaborate with Solutions Architects on enterprise customer implementations

• Support Customer Success with debugging and optimization

Requirements

Experience & Skills

• 3+ years of backend development experience building scalable systems

• Strong proficiency in Python

• Deep experience with relational databases (PostgreSQL) and SQL optimization

• Experience with graph databases (Neo4j, Amazon Neptune, or TigerGraph)

• Expertise in API design (REST, GraphQL) and microservices architecture

• Familiarity with cloud services (AWS, GCP, or Azure)

• Strong problem-solving and debugging skills

• Experience with distributed systems and message queues (RabbitMQ, Kafka)

Knowledge Graph Experience (Strongly Preferred)

• Built and maintained knowledge graphs or graph databases in production

• Experience with graph query languages (Cypher, Gremlin, SPARQL)

• Understanding of graph algorithms (shortest path, community detection, centrality measures)

• Knowledge of entity resolution and relationship extraction

• Experience with semantic web technologies and ontologies

AI/ML Infrastructure (Nice to Have)

• Experience serving ML models in production (TensorFlow Serving, MLflow, or similar)

• Knowledge of vector databases (Pinecone, Weaviate, Milvus) for semantic search

• Familiarity with LLM integration and prompt engineering

• Experience with feature stores and ML pipelines

• Understanding of NLP preprocessing and text analysis

Technical Skills

• Languages: Python (FastAPI, Django), Node.js, Go, or similar

• Databases: PostgreSQL, Neo4j, Redis, MongoDB

• Cloud: AWS (Lambda, RDS, S3, ECS) or GCP/Azure equivalents

• Message Queues: RabbitMQ, Apache Kafka, AWS SQS

• Monitoring: Datadog, New Relic, Prometheus, Grafana

• CI/CD: GitHub Actions, Jenkins, CircleCI

• Containerization: Docker, Kubernetes

• Version Control: Git, GitHub

Bonus Points

• Built real-time data processing systems at scale (millions of events/day)

• Experience with multi-tenant SaaS architectures

• Knowledge of security compliance (SOC 2, GDPR, HIPAA)

• Contributed to open-source projects

• Experience with WebSocket and real-time communication protocols

• Built integration platforms or iPaaS solutions

• Understanding of product analytics and instrumentation

Tech Stack You'll Work With

Backend Framework: Python + FastAPI
Databases: PostgreSQL (relational), Neo4j (knowledge graph), Redis (cache)
Cloud Infrastructure: AWS (Lambda, ECS, RDS, S3, SQS)
Message Queue: RabbitMQ / Apache Kafka
AI/ML: TensorFlow, PyTorch, Hugging Face Transformers
Vector Database: Pinecone for semantic search
Monitoring: Datadog + Sentry
API Gateway: Kong or AWS API Gateway
Authentication: Auth0 with OAuth 2.0 + SAML SSO

Benefits & Perks

Compensation & Equity

• Competitive market-rate salary

• Meaningful equity in a high-growth startup

• Annual performance bonuses

Work & Life Balance

• Remote-first, flexible work culture

• Unlimited PTO (we actually encourage you to use it)

• Flexible working hours across timezones

• Paid time off & team retreats

Team & Culture

• Small, high-impact team where your work matters

• Direct collaboration with founders

• Shape technical architecture and decisions

• Build products that transform how companies understand customers