
Backend Engineer
Posted Aug 28

Posted Aug 28
This is a fully remote position, open to applicants in United States, +1 more country.
• Develop high-performance, low-latency backend services to support AI agent operations.
• Create workflow orchestration systems for intricate, multi-step enterprise processes.
• Implement rule engines and policy enforcement mechanisms to ensure enterprise compliance.
• Design APIs and integrations with ERPs, procurement tools, payment systems, and data providers.
• Build systems for observability, auditing, and traceability in AI-driven decision-making.
• Construct secure data pipelines that manage sensitive financial and operational information.
• Develop agent execution runtimes, facilitate multi-agent coordination, and establish observability pipelines.
• Create evaluation frameworks and automated testing harnesses to ensure agent reliability and output quality.
• Design and develop scalable backend services following contemporary system design principles.
• Oversee services that manage procurement, invoicing, contract, and payment workflows.
• Implement orchestration that coordinates AI agents, human operators, and enterprise systems.
• Build resilient systems incorporating idempotency, retries, and effective failure management.
• Maintain APIs utilized by AI services, frontend applications, and external systems.
• Normalize and transform complex data across various enterprise systems.
• Instrument agent execution with trace capture, including tool calls, LLM I/O, latency, token usage, and costs.
• Define and monitor agent reliability metrics.
• Design enterprise-grade monitoring, alerting, access controls, audit logs, and data security measures.
• Ensure compliance with regulations for financial and sensitive data.
• Optimize for latency, throughput, and cost efficiency.
• Design services that scale to serve global customers and process billions of transactions.
• Identify and resolve bottlenecks in distributed systems.
• Extensive experience in building production-level backend systems.
• Proficient in Python, NodeJS, Go, or other similar backend programming languages.
• In-depth knowledge of distributed systems, APIs and microservices, SQL and NoSQL databases, and message queues/event-driven architectures.
• Demonstrated experience in designing scalable and fault-tolerant systems.
• Strong understanding of the trade-offs related to consistency, concurrency, and data integrity.
• Familiarity with financial systems, enterprise SaaS platforms, or handling sensitive/regulated data.
• Ability to operate effectively in environments where backend failures can significantly impact business operations.
• Experience with workflow engines or state-driven systems is advantageous.
• Prior experience in multi-agent orchestration and communication protocols is a plus.
• Knowledge of event sourcing, rule engines, or policy systems is beneficial.
• Experience with production debugging at scale and observability tools is a plus.
• Contributions to or experience with open-source LLM tooling ecosystems is a plus.
• Familiarity with agent observability tools and evaluation design is a plus.
• Experience in building LLM-powered systems in production and knowledge of agent frameworks is a bonus.
• Work from anywhere in the US & India.
• Enjoy a remote and travel-oriented work setup.
• Fully covered trips to the headquarters in Chennai as necessary.
• Opportunity to engage with cross-functional teams.
• High level of autonomy and responsibility.
• Contribute to visible work within a Series C company of around 100 employees.
• Professional development opportunities through continued learning and proactive engagement.
OneDome
IDS Comercial
Get handpicked remote jobs straight to your inbox weekly.