Senior Software Engineer - AI Agent Platform
Tasks
- Build resilient LLM and model serving integrations
- Build reusable APIs and abstractions for agent developers
- Create observability for AI requests including logs metrics tracing and alerts
- Define dashboards alerts SLOs and runbooks for production workloads
- Design agent execution and tool calling platform capabilities
- Drive incident follow up improvements
- Ensure production reliability during external outages
- Implement retries timeouts circuit breakers and graceful degradation
- Implement state management persistence and long running workflows
- Improve scalability concurrency latency and resource efficiency
- Investigate production issues across distributed systems and providers
- Mentor engineers and establish best practices
- Own runtime for executing and orchestrating AI agents
- Strengthen quality with integration testing load testing and failure injection
Perks/Benefits
Skills/Tech-stack
API Design | AWS | Agentic patterns | Amazon S3 | Caching | Chaos Engineering | Circuit Breaker | Circuit Breaker Monitoring | Circuit Breakers | Consistency | Context windows | Distributed Systems | Event Driven | Event-driven architecture | Failure injection | Failure recovery | Fallback strategies | Grafana | Idempotency | Integration Testing | Kafka | Kubernetes | LLM APIs | Latency optimization | Load Testing | Metrics | Multi-step Workflows | NestJS | Node.js | Observability | Provider Routing | Rate Limiting | Reasoning loops | Redis | Retries | SLO | STEP Workflows | Streaming | Structured Logging | Structured outputs | Timeouts | Token Management | Tool orchestration | Tool-Calling | Tracing | TypeScript
Education
Related jobs
-
Forward Deployed Engineer ILS 402K-504KAPI Development | AWS | Agentic AI | Azure | CI/CDClient-facing work | Cross-functional team collaboration | Hybrid workSenior-level Full TimeTel Aviv, Tel Aviv District, IL22h ago
-
Senior-level Full TimePetah Tikva, Center District, IL22h ago
-
Senior-level Full TimeTel Aviv-Yafo, Tel Aviv District, IL1d ago
-
Software Engineer - Data Pipelines ILS 200K-240KAWS Lambda | AWS S3 | Amazon EMR | Amazon SNS | Amazon SQSOn-call supportMid-level Full TimeIsrael - Office - Tel Aviv1d ago
-
API Gateway | AWS Bedrock | AWS Lambda | Amazon API | Amazon API GatewayFlexible working hours | Mentoring | Professional developmentSenior-level Full TimeRa'anana, Center District, IL1d ago
-
Senior Machine Learning Engineer USD 150K-200KAPI Development | AWS SageMaker | Data Pipelines | FastAPI | Feature EngineeringSenior-level Full TimeTel Aviv-Yafo, Tel Aviv District, IL1d ago
-
Airflow | Apache Kafka | Apache Spark | Bash | CI/CDSenior-level Full TimeTel Aviv-Yafo, Tel Aviv District, IL2d ago
-
Mid-level Full TimeTel Aviv, Israel2d ago
-
Senior-level Full TimeTel Aviv, Israel2d ago
-
APIs | AWS | AWS Lambda | Amazon RDS | Amazon S3Autonomy | Collaborative team environment | Continuous learning | High ownership | Professional growthSenior-level Full TimeIsrael2d ago
-
Mid-level Full TimeRa'anana, Center District, IL2d ago
-
Senior-level Full TimeTel-Aviv3d ago
-
API Design | Analytical Engine | Automated testing | CI/CD | Cloud platformMid-level Full TimeRamat Gan, Israel, IL3d ago
-
AWS | Apache Kafka | Capacity Planning | Distributed Systems | Fault ToleranceSenior-level Full TimeTel Aviv/ Hybrid (Israel), Israel R3d ago
-
DevOps Team Leader - Infra and DevEx ILS 420K-504KAI Agents | AI coding | AI coding tools | AWS EKS | AWS IAMDevelopment programs | Flexible work schedule | Hybrid work | Mental health insurance | Occasional long weekendsSenior-level Full TimeBnei Brak, Tel Aviv District, IL3d ago
-
Reindeer- Software Engineer (Infrastructure) USD 180K-250KAPI Integration | AWS | Authentication | Authorization | AzureSenior-level Full TimeTel Aviv-Yafo, Tel Aviv District, IL3d ago
-
Principal/Senior ML Platform Engineer (Cortex) ILS 420K-504KAWS | Azure | CI/CD | Data Drift | Data drift monitoringSenior-level Full TimeTel Aviv, Tel Aviv4d ago
-
API Integration | Data Pipelines | Evaluation | Information Retrieval | Language ModelsEquity | Fast-learning environment | Real ownership | Remote-friendlyMid-level Full TimeTel Aviv-Yafo, Tel Aviv District, Israel5d ago
-
Senior-level Full TimeJerusalem, Israel7d ago
-
Mid-level Full TimeTel Aviv-Yafo, Tel Aviv District, Israel8d ago
-
Senior-level Full TimeTel Aviv/ Hybrid (Israel), Israel R8d ago
-
Airflow | Amazon SageMaker | Apache Beam | Argo Workflows | Attention MechanismsSenior-level Full TimeTel Aviv/ Hybrid (Israel), Israel R8d ago
-
Mid-level Full TimeTel Aviv/ Hybrid (Israel), Israel R8d ago
-
Senior Data Engineer — Data Platform ILS 420K-504KAWS | AWS Glue | Airflow | Alerting | Apache IcebergSenior-level Full TimeTel Aviv-Yafo, Tel Aviv District, IL8d ago
-
AWS | Apache Kafka | Capacity Planning | Distributed Systems | JavaHybrid work | Learning and development | Modern technology stackSenior-level Full TimeTel Aviv/ Hybrid (Israel), Israel R8d ago