5 hours ago
Responsibilities
- Design and develop MCP Gateway and AI Gateway production services for applications, AI agents, and LLM providers.
- Implement protocol-level capabilities including MCP clients and servers, request routing, streaming, tool-call proxying, authentication and authorization, and tenant isolation.
- Build high-throughput, low-latency network services involving TCP, TLS, HTTP, JSON streaming, connection pooling, and backpressure.
- Own application-side PostgreSQL schema design, indexing, query planning, transactions, isolation, connection management, and migrations at scale.
- Design concurrent systems using worker pools, queues, graceful shutdown, backpressure, and race-free shared state.
- Profile services under load and resolve performance bottlenecks involving allocations, garbage collection, lock contention, and query performance.
- Build observability for AI systems covering metrics, tracing, logging, token usage, provider latency, cache hit rates, failure modes, and cost per request.
- Deploy, debug, monitor, and continuously improve reliable distributed services in containerized environments.
- Participate in technical design discussions and code reviews, and help shape AI-assisted development workflows and internal tooling.
Requirements
- 5+ years of senior-level experience in Go, Ruby, or both, including shipping and operating production services.
- For Go, deep knowledge of the standard library, net/http, crypto/tls, context, goroutines, channels, the memory model, networking, and performance optimization.
- For Ruby, strong production Rails experience, including understanding Ruby internals and tuning ActiveRecord for performance under load.
- Deep application-developer knowledge of PostgreSQL, including query optimization, indexing, transactions, connection pooling, and large-scale migrations.
- Practiced experience with concurrency, profiling, and debugging production incidents.
- Familiarity with Kubernetes and containers, including resource limits, health checks, rolling deployments, and networking basics.
- Experience building production services with observability, deployment pipelines, security, and distributed-systems troubleshooting.
- Protocol-level LLM experience with message structures, tool calling, streaming responses, and caching strategies.
- Familiarity with MCP, including MCP server or client integration and transport and capability negotiation, is strongly preferred.
- Experience integrating directly with OpenAI-compatible and Anthropic APIs, evaluating responses, understanding token usage, and optimizing latency and cost.
- Ability to audit and verify LLM output and identify subtle bugs, security issues, and hallucinated APIs.
- Ability to learn quickly, evaluate evolving AI protocols, communicate complex concepts clearly, and own systems across design, implementation, deployment, and monitoring.
Benefits
- Flexible, trust-oriented culture with substantial ownership and support for work-life balance.
- Access to nearly every major AI coding tool, IDE, and frontier model with generous usage limits.
- Opportunity to shape AI-assisted development workflows, agent processes, code-review automation, and internal tooling.
- Role based in Singapore.
Tech Stack
Categories
About Workato
Workato is the leading Control and Execution Platform for Enterprise AI – the neutral platform enterprises trust to put AI to work across their business. We connect to every app, system, and process your business runs on, with no data migration, no rip-and-replace, so AI can reliably orchestrate business processes in production, at enterprise scale. Built on more than a decade of running mission-critical processes for over half the Fortune 500, including Nasdaq, Amazon, Cisco, Vodafone, Atlassian, and Lucid Motors, Workato turns 14,000+ enterprise systems into one governed execution layer. AI has solved reasoning. The next frontier is execution, with Workato.