AI Platform Engineer

Description

Invent the future with us.

Ampere is a semiconductor design company for a new era, leading the future of computing with an innovative approach to CPU design focused on high-performance, energy efficient AI compute.

As a pioneer in the new frontier of energy efficient high-performance computing, Ampere is part of the Softbank Group of companies driving sustainable computing for AI, Cloud, and edge applications.

Join us at Ampere and work alongside a passionate and growing team - we’d love to have you apply!

About the role:

Ampere is hiring a senior individual contributor to build the engineering foundation for enterprise AI. The role covers platform services, knowledge and retrieval systems, MCP integrations, and agent workflows.

This is a hands-on engineering role. You will make design decisions, write production code, establish technical standards, and remain accountable for the systems after release. You will work with engineering, data, IT, security, and business teams to deliver AI capabilities that are secure, reliable, and useful.

What you’ll achieve:

• Build and operate shared services, APIs, automations, and integrations that allow teams to use approved AI models, enterprise data, and business tools.
• Improve reliability, performance, deployment, monitoring, logging, incident response, and operating documentation.
• Set implementation standards and build common components that reduce duplicated work across AI initiatives.
• Develop embedding, indexing, and retrieval methods for technical and enterprise knowledge.
• Improve search quality through hybrid retrieval, metadata filtering, access-aware retrieval, reranking, query processing, source citations, and evaluation.
• Apply appropriate data structures and algorithms to search, ranking, caching, state management, and performance.
• Build test sets and measurement methods for retrieval accuracy, grounding, latency, cost, and failure handling.
• Design and implement MCP clients, servers, and tool integrations for enterprise systems.
• Define tool interfaces, schemas, authentication, authorization, approval flows, audit records, and lifecycle practices.
• Build and maintain integrations with engineering, knowledge, ticketing, source-control, data, and business systems.
• Maintain a managed tool catalog with ownership, access controls, versioning, test coverage, monitoring, and retirement practices.
• Build agent workflows that plan tasks, call tools, retain execution state, request approval when needed, and recover from failure.
• Implement scheduling, retries, checkpoints, cancellation, escalation, and human review for long-running work.
• Set controls for agent permissions, credential scope, tool risk, evidence capture, and auditability.
• Measure task completion, tool outcomes, workflow quality, latency, reliability, and cost.
• Apply enterprise identity and security requirements across AI services, including OAuth2/OIDC, SSO, managed identities, RBAC, secrets management, and least-privilege access.
• Address prompt injection, data leakage, unsafe tool access, excessive permissions, and poor source provenance.
• Work with security and platform teams to maintain the controls, monitoring, and operating practices required for enterprise AI

About you:

• M.Tech in Computer Engineering or related field with 3+ years of experience or B.Tech in Computer Engineering or releated field with 5+ years of experience
• 3+ years of experience building production software, platform services, developer tools, data systems, or applied AI products.
• Strong software-engineering fundamentals, including data structures, algorithms, API design, schema design, asynchronous systems, testing, debugging, and performance analysis.
• Strong programming skills in Python and TypeScript, plus experience building and maintaining React applications.
• Experience building APIs, integrations, background jobs, automations, and services that use enterprise authentication and authorization.
• Experience with LLM applications, tool calling, structured outputs, semantic search, retrieval systems, or agent workflows.
• Experience with embeddings, hybrid search, metadata design, ranking, access-aware retrieval, retrieval evaluation, and vector or search infrastructure.
• Experience with MCP or comparable tool-integration protocols, including tool contracts, schemas, authentication, authorization, and lifecycle management.
• Experience designing reliable workflows with state management, retries, idempotency, checkpoints, cancellation, and audit trails.
• Working knowledge of Linux, Git, Docker, CI/CD, cloud deployment, monitoring, logging, and production incident response.
• Sound security judgment across identity, access control, secrets, sensitive data, and AI-specific threats

Preferred Qualifications:

• Rust and Tauri experience, or experience building native desktop applications.
• Azure experience, including Azure AI Foundry, Azure OpenAI, Azure AI Search, Azure Monitor, Application Insights, Key Vault, Microsoft Entra ID, managed identities, and Azure VMs.
• Experience with search and vector platforms such as Azure AI Search, Elasticsearch/OpenSearch, Qdrant, Weaviate, Pinecone, or Chroma.
• Experience with workflow orchestration, event-driven systems, queues, schedulers, state machines, or durable execution platforms.
• Infrastructure-as-code experience with Terraform, Bicep, or similar tools.
• Experience with Redis, caching, rate limiting, telemetry, usage analytics, capacity planning, or cost management.
• Experience with pytest, Vitest, Playwright, contract testing, integration testing, or AI evaluation frameworks.
• Experience in semiconductor, advanced computing, developer platform, or enterprise engineering environments.

What we’ll offer:

At Ampere we believe in taking care of our employees and providing a competitive total rewards package that includes base pay, cash long-term incentive, and comprehensive benefi