You Are:

As an Advanced AI Full Stack Engineer, you will design and build the foundational systems that power AI agent platforms — from agent orchestration runtimes and sandboxed execution environments to inference routing layers, SDK tooling, and developer-facing APIs. You are a software engineer first, with deep fluency in Python and Node.js, who thrives at the intersection of distributed systems, AI infrastructure, and developer experience. You will work across the full platform stack — from CLI tooling and event-streaming protocols to multi-tenant Kubernetes-based execution environments — shipping production systems that other engineers and AI agents depend on.

The Work:

Platform & Runtime Engineering:

• Design and build agent orchestration runtimes — stateful execution loops that coordinate tool discovery, model inference, approval gates, and context management.

• Implement sandboxed execution environments with declarative policy enforcement (network egress, filesystem, compute quotas) that isolate agent workloads at the infrastructure level.

• Develop pluggable provider interfaces so that sandbox backends (container-based or microVM-based) are swappable without changing agent code.

SDK, API & Developer Tooling:

• Build Python and Node.js/TypeScript SDKs and CLIs that give developers first-class interfaces for authoring, validating, and running AI agents locally and in enterprise environments.

• Design REST, gRPC, and event-streaming APIs (WebSocket, SSE) that serve as the communication backbone between agent runtimes, IDE integrations, and platform services.

• Implement framework adapters that normalize event streams from multiple AI frameworks into a unified platform event model, enabling consistent observability and governance regardless of the underlying agent framework.

Inference Routing & Memory Systems:

• Build and maintain intelligent inference routing layers that intercept model API calls and dispatch them to on-premise or cloud model endpoints based on data-sovereignty, cost, and capability policies.

• Engineer multi-tier memory architectures spanning in-process working memory, cross-session relational stores, vector databases for semantic retrieval, and version-controlled procedural pipelines — each backed by swappable provider interfaces.

• Implement ephemeral credential injection and RBAC-scoped data access so agents operate under least-privilege principles without long-lived secrets in agent code.

Observability, Governance & CI/CD:

• Instrument platform components with distributed tracing (OpenTelemetry), cost attribution, and P50/P95/P99 latency metrics exportable to standard observability backends.

• Build CI/CD governance tooling — static validation pipelines that enforce schema correctness, separation-of-duty rules, and regulatory constraints before agent packages are promoted to production registries.

• Implement human-in-the-loop approval gates and audit-trail mechanisms compatible with enterprise compliance requirements.

Collaboration & Technical Leadership:

• Work closely with cross-functional teams — AI researchers, product managers, security engineers, and enterprise architects — to align platform capabilities with real-world agent use cases.

• Provide technical guidance on platform architecture decisions, code reviews, and engineering best practices across the team.

• Communicate architectural trade-offs and platform roadmap decisions clearly to both technical and non-technical stakeholders.

Travel may be required for this role. The amount of travel will vary from 0 to 100% depending on business need and client requirements.

This role requires working onsite in Mountain View, CA. Applicants must be local to Mountain View area or willing to relocate prior to joining.

Here's what you need

• Bachelor's degree (or equivalent minimum 12 years work experience, or minimum 6 years' work experience with Associate's degree) in Computer Science, Computer Engineering, or a related field.

• Minimum of 2 years of experience with Python and/or Node.js/TypeScript building production backend services or platform tooling.

• Minimum of 1 year of experience building or integrating with AI/LLM systems, agent frameworks, or AI developer tooling.

Bonus point is you have

• 4+ years of experience with Python and Node.js/TypeScript, with a strong track record of building and shipping developer-facing platforms, SDKs, or APIs.

• 2+ years of experience in one or more of: agent orchestration frameworks, inference serving infrastructure, sandboxed execution environments, or multi-tenant platform engineering.

• Hands-on experience with async Python frameworks (FastAPI, asyncio), containerisation and Kubernetes, event-streaming protocols (WebSocket, SSE, gRPC), and vector/relational databases.

• Familiarity with AI agent protocols (MCP, ACP, A2A), OpenTelemetry instrumentation, and modern AI framework ecosystems (LangGraph, OpenAI Agents SDK, Anthropic Claude SDK).

• Master's or PhD in Computer Science, Computer Engineering, or a related field is a plus but not required.

Compensation at Accenture varies depending on a wide array of factors, which may include but are not limited to the specific office location, role, skill set, and level of experience. As required by local law, Accenture provides a reasonable range of compensation for roles that may be hired as set forth below.
We anticipate this job posting will be posted until 06/30/2026.

Accenture offers a market competitive suite of benefits including medical, dental, vision, life, and long-term disability coverage, a 401(k) plan, bonus opportunities, paid holidays, and paid time off. See more information on our benefits here:

Role Location Annual Salary Range
California $73,800 to $220,400
Cleveland $68,300 to $176,300
Colorado $73,800 to $190,400
District of Columbia $78,500 to $202,700
Illinois $68,300 to $190,400
Maryland $73,800 to $190,400
Massachusetts $73,800 to $202,700
Minnesota $73,800 to $190,400
New York $68,300 to $220,400
New Jersey $78,500 to $220,400
Washington $80,200 to $202,700

#LI-NA-FY25