Position Summary:

The AI Software Engineer is responsible for the hands-on development, maintenance, and expansion of our enterprise AI Platform as a Service. In this role, you will be a key contributor to building the 'Operating System for Intelligence,' developing the shared services, standardized interfaces, and agentic orchestration modules that enable the organization to deploy semantic discovery, conversational intelligence, and autonomous agents. This role will move beyond building isolated applications to engineering a scalable, multi-tenant execution architecture using a managed Agent Runtime Environment. Your mission is to maintain the platform's core infrastructure while building specialized supervisor agents and standardized toolsets that serve as the modular building blocks for enterprise-wide automation.

Job Duties/Essential Functions:

- Maintain and evolve core AI platform services, such as shared memory banks and session management. This includes managing the central reasoning engine.
- Architect and optimize modular agentic framework templates using standardized orchestration SDKs to manage complex, stateful workflows.
- Create and maintain a library of standardized capability servers using the model context protocol, enabling agents to securely orchestrate tasks across enterprise data platforms, customer relationship management systems, and distributed microservices.
- Integrate the AI Platform as a Service with existing enterprise infrastructure. This includes developing code for authentication systems, logging pipelines, and CI/CD workflows.
- Manage and optimize the platforms semantic retrieval architecture, ensuring high-speed, low-latency access to grounded enterprise knowledge through a unified discovery and retrieval engine.
- Engineer and optimize discovery agents that leverage semantic retrieval and neural search platforms to ingest, validate, and cite evidence from unified multimodal lakehouses.
- Establish Agent Identity (IAM) protocols to ensure every autonomous action is authenticated, authorized, and logged under a secure service principal.
- Implement and scale automated AI performance benchmarking systems to continuously monitor mission success rates and proactively identify regressions in reasoning, safety guardrails, or autonomous decision-making.




- Serve as the primary responder for systemic platform anomalies, utilizing distributed traceability and aggregated telemetry to diagnose and resolve bottlenecks within complex multi-agent reasoning chains.
- Maintain internal documentation and SDKs that empower other software teams to onboard their use cases onto the AI Platform as a Service.
- Ensures the longevity, scalability and quality of our systems through continuous improvement, comprehensive documentation, meticulous profiling, and significant performance enhancements.
- Regular and reliable workplace attendance at your assigned location.

Ability to operate vehicles, equipment or machinery:

- Computer, phone, printer, copier, fax.

Non-Essential Functions:

- Assists in other areas of the department as necessary.
- Assists in other areas of the company as necessary.

Ability to operate vehicles, equipment or machinery:

- Same as Essential Functions

Experience, Skills, Education & Licenses/Certifications:

Required:

- 12+ years years of experience in backend software development with a focus on API design and microservices.
- 1+ years of hands-on experience building with LLM APIs, function calling, or orchestration frameworks.
- Expertise experience architecting and maintaining containerized autonomous workloads across elastic container orchestration and scalable serverless runtimes, with a focus on high-availability event-driven architectures.
- Extensive experience managing high-scale semantic indices and engineered multimodal data pipelines that unify structured relational repositories with unstructured knowledge for agentic grounding.
- Expert-level proficiency in asynchronous orchestration frameworks utilizing type-safe schema validation and high-performance API gateways. Complementary mastery of statically typed systems for engineering highly concurrent, low-latency agentic backend infrastructure..




- Expert mastery of stateful graph orchestration and multi-agent coordination frameworks, with a proven ability to design complex cyclic reasoning loops and automated task delegation systems.
- Proficiency in architecting semantic retrieval layers, attribute-aware discovery, and stateful persistence systems to provide high-fidelity long-term context for autonomous agents.
- Deep understanding of MCP, A2A, REST/gRPC APIs, Oauth2 security, and function calling mechanics.
- Infrastructure as Code and CI/CD for prompt engineering and model deployment.
- Experience leading technical workstreams, translating business problems into AI-native architectures.
- 5+ years of experience with API development, with an emphasis on security and performance.
- 5+ years of experience with microservice-based debugging and performance testing.
- 5+ years of experience developing within an agile methodology.
- Strong verbal and written communication skills and be able to communicate to both technical and Business audiences.
- Ability to work under pressure in crisis with a strong sense of urgency.
- Responsible, conscientious, organized, self-motivated and able to work with limited supervision.
- Detail-oriented and possess strong problem-solving skills and ability to analyze potential future issues.
- Able to support off-hours work as required, including weekends, holidays, and 24/7 on-call responsibilities on a rotational basis.

Recommended:

- Bachelors degree in Computer Science, Software Engineering, or a related technical field.
- Masters degree or PhD with a focus on Distributed Systems, AI Orchestration, or Machine Learning.
- Google Cloud Qualified Data Engineer, Google Cloud Professional Cloud Architect, or any Agentic AI Specialty Certification focusing on Multi-Agent Systems and Autonomous Reasoning.
- 3+ years distributed cache technologies
- Experience with deploying and configuring Cloud Platform resources.
- Experience working in a retail ecommerce environment.
- Proficient in Google Workspace applications, including Sheets, Docs, Slides, and Gmail.
- Successful internal candidates will have spent one year or more on their current team.

Other Conditions:

Management will review the Job Analysis for this position prior to a job offer.

📌 Software Engineer - AI - Innovation Engineering (India)
🏢 Costco
📍 India