Senior AI Engineer

About Workato

Workato is the foremost Control and Execution Platform dedicated to Enterprise AI, serving as a trusted neutral platform enabling enterprises to leverage AI throughout their operations. It integrates data, applications, and business processes into a unified platform, allowing AI to orchestrate enterprise-grade production workflows. Supporting over half of the Fortune 500 companies—including Nasdaq, Amazon, Cisco, Vodafone, Atlassian, and Lucid Motors—Workato manages more than 14,000 enterprise systems within a comprehensive governed execution layer.

We foster a culture rooted in flexibility and mutual trust, empowering all team members to take ownership of their roles. Driven by innovation, we seek collaborative team players eager to contribute actively to the company’s growth. We emphasize a balance between productivity and well-being, offering a dynamic and engaging work environment with numerous benefits that span both professional and personal life.

Our achievements include recognition by Business Insider as a top enterprise startup to invest your career in, inclusion in Forbes’ Cloud 100 list of the world's best private cloud companies, ranking 17th in the Deloitte Tech Fast 500 for the Bay Area, 96th in North America, and being named the top company for remote workers by Quartz.

Role and Responsibilities

The role focuses on developing the foundational infrastructure layer that bridges enterprise systems and AI. This includes building and maintaining the MCP Gateway, AI Gateway, and accompanying services that function as intermediaries between Large Language Model (LLM) providers and enterprise applications. Responsibilities encompass protocol engineering, such as MCP server/client implementation, request routing, streaming, proxying tool calls, authentication and authorization, and tenant isolation. The position prioritizes creating the core infrastructure itself rather than merely higher level applications.

Key duties include designing and implementing high-throughput, low-latency network services with expertise in TCP, TLS, HTTP/1.1 & HTTP/2, JSON streaming, connection pooling, and managing backpressure. The engineer will also manage the data layer with strong PostgreSQL knowledge, handling schema design, indexing, query optimization, transaction management, and connection pooling while analyzing EXPLAIN ANALYZE outputs to diagnose and resolve performance issues.

Concurrency design such as worker pools, queues, graceful shutdown, backpressure handling, and race-free shared state is critical. Profiling services under load using pprof, flamegraphs, and query statistics to find and fix bottlenecks is expected. The role also requires advancing observability by implementing metrics, tracing, and logging focused on token usage, latency per provider, cache efficiency, failure modes, and cost per request.

How We Engage With AI

• AI/LLM assisted development is encouraged but not mandatory, with a focus on quality output regardless of tooling.
• A wide array of top AI tools and models are accessible with generous usage allowances to foster innovation.
• The team actively explores and refines automated development practices including AI-assisted workflows, code review automation, and internal tooling enhancement.
• Engineers leverage LLM tools to attain full product visibility across all domains (frontend, backend, infrastructure, documentation) and maintain end-to-end ownership of solutions.
• Accountability remains personal; all output must be justifiable without relying on AI-generated suggestions as sole rationale.

Required Qualifications and Skills

• At least 5 years of significant experience in Go, Ruby, or both, with a proven record of shipping and operating production-grade services.
• For Go developers: in-depth knowledge of the standard library (net/http, crypto/tls, context, goroutines, channels), performance tuning, memory management, garbage collection, lock contention, and strong understanding of networking protocols including TCP, TLS, HTTP, and JSON.
• For Ruby developers: extensive production experience with Rails and Ruby, adeptness at tuning ActiveRecord for strong performance under load, and a clear grasp of the Ruby ecosystem beyond Rails.
• Advanced understanding of PostgreSQL from the application development viewpoint, including query and index optimization, transactions, connection pooling, and large-scale migrations.
• Proficient in handling concurrency and performance profiling to troubleshoot and resolve production issues.
• Familiarity with Kubernetes and container ecosystems, including deploying, debugging, and maintaining services with resource constraints, health checks, rolling updates, and basic networking.
• Experience developing production systems with observability, secure deployment pipelines, and capability to troubleshoot complex distributed systems.
• Experience working with LLMs at the protocol level, including message formats, tool calling, streaming responses, and caching techniques.
• Knowledge of MCP (Model Context Protocol) is highly advantageous, especially in building or integrating MCP servers/clients and understanding transport and negotiation layers.
• Ability to work directly with OpenAI-compatible and Anthropic APIs, assessing responses, managing token usage, and optimizing latency and cost.
• Skill in auditing and verifying LLM outputs to detect subtle issues, security vulnerabilities, and hallucinations, with solid understanding of underlying system mechanics.

Personal Traits

• Quick learner who stays updated on evolving AI infrastructure and can rapidly evaluate novel protocols and technologies.
• Engages actively in design discussions and code reviews with the ability to convey complex ideas clearly to technical and non-technical audiences.
• Comfortable managing the entire software lifecycle—from conception and coding to deployment and continuous monitoring/improvement.