About the Role

Most Important

• 5+ Years of Experience: Proven background in platform engineering, API infrastructure, or high-scale backend production systems.

• API Gateway Operations: Production experience configuring, deploying, and operating API gateways at scale (Kong strongly preferred; Envoy, Apigee, or Istio accepted).

• LLM Provider Integration: Hands-on experience integrating model provider APIs (Anthropic, AWS Bedrock, OpenAI) into enterprise application architectures.

• Auth & Credential Management: Deep working knowledge of RBAC/OIDC protocols, API key lifecycle management, and secret/key rotation practices.

• Caching & Performance: Experience deploying caching layers (Redis or similar) for latency reduction, semantic caching, or cost optimization.

• Core Languages: Strong proficiency in Python or Go for building platform automation, custom gateway plugins, and core infrastructure tooling.

Nice to Have

• MCP & Registry Experience: Familiarity with Model Context Protocol (MCP) or comparable service-registry and service-mesh patterns for autonomous AI agents.

• Advanced AI Caching: Hands-on exposure to vector databases or semantic caching mechanisms specifically tuned for GenAI/LLM payloads.

• AI Proxy Tooling: Prior exposure to modern AI proxy frameworks or AI management platforms (e.g., Initializ AI, Portkey, LiteLLM).

Personal Traits

• Problem-Solving & Value-Driven Communicator: Possesses strong behavioral and technical communication skills; able to articulate complex technical decisions, approach problem-solving methodically using frameworks like the STAR method, and clearly demonstrate business value.

• Agile & Adaptable: Thrives and stays comfortable operating within a fast-moving platform engineering team with continuously evolving standards, tools, and practices.

• Security & Operational Mindset: Prone to proactive risk management; takes a rigorous approach to enterprise security, zero-trust architectures, credential lifecycle management, and high-availability systems.

• Cost & Ownership Conscious: Possesses a strong sense of end-to-end accountability for production systems, keeping a close eye on system performance, token usage, and granular cost attribution across teams and agents.

• Collaborative Platform Facilitator: Acts as a trusted partner to downstream internal development and AI agent teams, making it easy and secure for other engineers to leverage central AI infrastructure without friction.