Текст заказа
About Us
============
Wellington Management offers comprehensive investment management capabilities that span nearly all segments of the global capital markets. Our investment solutions, tailored to the unique return and risk objectives of institutional clients in more than 60 countries, draw on a robust body of proprietary research and a collaborative culture that encourages independent thought and healthy debate. As a private partnership, we believe our ownership structure fosters a long-term view that aligns our perspectives with those of our clients.
About the Role
==============
Lead AI Engineer, Enterprise AI Platform
========================================
Location: Boston, MA / Hybrid
Level: Lead / Senior Individual Contributor
Organization: Enterprise AI
Role Summary
------------
The Lead AI Engineer will design, build, and operationalize the shared enterprise platform used to develop, deploy, and operate production AI applications and agents safely at scale.
This is a senior, hands-on role at the intersection of software and platform engineering, agentic AI development, cloud infrastructure, security, and developer experience.
The role will turn enterprise architecture into reusable services, APIs, SDKs, infrastructure automation, and engineering standards. The platform is anchored on Microsoft Azure and Microsoft Foundry, including Foundry Agent Service and hosted agents, and operates within a pragmatic multi-cloud and multi-model environment. The emphasis is on building durable engineering capabilities rather than relying on any single product.
Success means making the governed path the fastest path for product and engineering teams.
Key Responsibilities
--------------------
Enterprise AI Platform Engineering
* Design and implement shared platform capabilities, including model access, agent runtimes, orchestration, gateways, MCP and tool integration, retrieval services, agent and tool registries, observability, evaluations, guardrails, and FinOps controls.
* Build reusable platform capabilities that enable application and business teams to deliver secure, observable, and resilient production solutions through streamlined self-service.
Agentic Application Development
* Establish patterns, frameworks, and reference implementations for building single-agent and multi-agent applications using technologies such as Microsoft Agent Framework or LangGraph.
* Develop standards for agent-to-agent interoperability, prompts, context, state, memory, human approvals, kill switches, retries, fallback, versioning, service-level objectives, and controlled promotion to production.
AI Gateway and Model Access
* Create a governed, model-agnostic access layer with authentication, identity propagation, routing, quotas, rate limits, failover, usage attribution, policy enforcement, and provider abstraction.
* Support model access across Azure, AWS, and approved on-premises services, including patterns such as Azure API Management in front of Foundry model deployments.
MCP and Enterprise Tools
* Build secure MCP servers and gateways.
* Define patterns for hosting, OAuth, delegated authorization, on-behalf-of identity, token exchange, tool discovery, registration, and allowlisting.
Identity, Security, and Entitlements
* Partner with Identity, Cybersecurity, and Cloud Engineering teams to implement enterprise identity controls.
* Develop workload and per-agent identity with lifecycle management and Conditional Access using Microsoft Entra ID and Entra Agent ID.
* Implement role-based access control, least privilege, app-registration automation, secrets elimination, cross-cloud federation, and entitlement-aware data access.
Agent Evaluation and Observability
* Design and operate agent evaluation frameworks and regression pipelines that measure task success, tool-use correctness, groundedness, safety, and use-case-specific outcomes.
* Use evaluations as automated quality gates for production promotion.
* Instrument agent runs, LLM requests, retrieval, tool calls, latency, errors, quality, policy events, token usage, and cost using OpenTelemetry-based standards where possible.
AI Safety, Risk, and Compliance
* Implement guardrails, content-safety controls, prompt-injection defenses, data-loss protections, red-team testing, audit trails, and agent and model inventories.
* Align platform capabilities with applicable regulatory and model-risk requirements, including the NIST AI Risk Management Framework, SR 11-7, and the EU AI Act where relevant.
Automation and Developer Experience
* Treat the platform as a product through Infrastructure as Code, CI/CD, automated test-to-stage-to-production promotion, policy as code, SDKs, templates, reference implementations, documentation, and self-service onboarding.
Technical Leadership Responsibilities
-------------------------------------
* Own significant platform capabilities from architecture through production operation.
* Make pragmatic build-versus-buy decisions and evaluate rapidly changing AI technologies without chasing every new framework.
* Establish engineering standards, reference architectures, code-review practices, and production-readiness criteria.
* Lead technically complex initiatives across AI, Cloud, Security, Data, Architecture, and product engineering teams.
* Mentor AI and platform engineers while reducing dependency on individual specialists or external resources.
* Communicate trade-offs, risks, sequencing, and investment needs clearly to engineers and senior leaders.
Required Qualifications
-----------------------
* Eight or more years of professional software, cloud, or platform engineering experience.
* Three or more years of experience building production machine learning or advanced data platforms.
* One to two or more years of experience delivering production LLM or agent-based systems.
* Demonstrated technical leadership for significant production systems.
* Strong hands-on software engineering skills in Python and at least one additional language, such as TypeScript, Java, C#, or Go.
* Deep experience with several of the following: LLM APIs, agentic architecture, tool or function calling, retrieval-augmented generation, embeddings, vector retrieval, context engineering, orchestration, model routing, observability, and MCP.
* Hands-on experience designing and operating agent evaluations, including test datasets, automated and LLM-as-judge scoring, tool-use and trajectory assessment, safety and groundedness checks, and regression gating within CI/CD.
* Strong cloud platform engineering experience, with depth in Microsoft Azure technologies such as Microsoft Foundry, Foundry Agent Service, model deployments, Azure AI services, API Management, Entra ID, private networking, Key Vault, Application Insights, Azure Monitor, Infrastructure as Code, and CI/CD.
* Experience building platform capabilities consumed by other engineering teams, including APIs, SDKs, self-service infrastructure, developer tooling, runtime controls, telemetry, and production support.
* Strong understanding of distributed systems, API design, reliability, security, identity, networking, and operational risk.
Preferred Qualifications
------------------------
* Experience with agent orchestration frameworks such as Microsoft Agent Framework or LangGraph.
* Familiarity with agent-to-agent interoperability and related standards.
* Experience developing MCP servers and implementing OAuth, on-behalf-of identity, and token-exchange patterns.
* Experience implementing Azure API Management or another AI gateway.
* Experience with OpenTelemetry, Kubernetes or AKS, Bicep or Terraform, and GitHub Actions or Azure DevOps.
* Familiarity with Microsoft Purview, Microsoft Fabric, Azure AI Search, and enterprise data-security controls.
* Experience with advanced evaluation practices, including adversarial testing, red-team testing, onli