AI 工程师 - 前线部署（Claude）

Role Overview

The AI Engineer is a hands-on builder who works directly with Client teams to design, build, and ship production AI solutions on Anthropic's Claude platform. This is an individual contributor role. You will write the code, build the agents and integrations, connect Claude to Client data, and get solutions into the hands of real users.

You will work inside a Collectiv delivery team alongside a project lead, architects, and data engineers. You will partner directly with Client business and IT stakeholders to turn a business problem into a working Claude solution, then harden it for production on the Microsoft data stack and beyond.

Key Responsibilities

Claude Solution Development

• Build agents, assistants, and knowledge search experiences using the Claude API, including tool use, extended thinking, structured outputs, prompt caching, and batch processing

• Build agentic workflows with the Claude Agent SDK, including multi-step orchestration, subagents, and human-in-the-loop controls

• Build and deploy Model Context Protocol (MCP) servers that connect Claude to Client systems such as Microsoft Fabric, Power BI, SharePoint, CRM, and ERP platforms

• Deploy Claude through the Anthropic API, Microsoft Foundry, Amazon Bedrock, or Google Vertex AI based on Client requirements

• Write and iterate on system prompts, tool definitions, and Agent Skills based on test results and user feedback

Claude for Enterprise and Claude Code

• Configure and roll out Claude for Enterprise, including connectors, Projects, Skills, and admin controls

• Use Claude Code to accelerate delivery, and help Client engineering teams adopt it with sound workflows, permissions, and guardrails

• Build reusable Skills, plugins, and prompt libraries that encode Client processes and standards

Retrieval and Data Foundations

• Build end-to-end retrieval-augmented generation (RAG) pipelines including ingestion, chunking, embedding, vector and hybrid search, and grounding

• Partner with Collectiv data engineers to connect Claude solutions to Microsoft Fabric, Databricks, and other enterprise data platforms

• Integrate Claude solutions with enterprise systems through APIs, Azure Functions, and event-driven architectures

Evaluation and Production Readiness

• Build evaluation sets and test harnesses that measure answer quality, groundedness, hallucination rate, safety, latency, and cost

• Implement logging, monitoring, tracing, and cost controls for deployed agents

• Apply security, identity, and data governance controls appropriate to each Client environment

• Use version control, CI/CD, and code review standards for all AI solution code and configuration

Consulting and Collaboration

• Work directly with Client stakeholders to gather requirements, run working sessions, demo progress, and manage expectations

• Translate business problems into scoped, buildable AI use cases with clear success metrics

• Train Client users and engineers on the solutions you build and support adoption after go-live

• Contribute reusable patterns, accelerators, and documentation to Collectiv's AI practice

Required Qualifications

• Bachelor's degree from an accredited university in Computer Science, Data Science, Engineering, or a related field (or equivalent experience)

• 4+ years of experience in software engineering, data engineering, or analytics engineering

• 1+ years of hands-on experience building and deploying generative AI or LLM-powered solutions in production or Client environments

• Hands-on experience with the Claude API, including tool use

• Experience building or deploying MCP servers

• Hands-on experience with Claude Code or the Claude Agent SDK

• Strong Python or TypeScript skills

• Experience building RAG solutions, including vector search and document ingestion

• Experience working in at least one major cloud (Azure preferred, AWS or Google Cloud also valued)

• Ability to work independently in a Client-facing consulting role

Preferred Qualifications

• Experience deploying Claude through Microsoft Foundry, Amazon Bedrock, or Google Vertex AI

• Experience rolling out Claude for Enterprise or Claude for Work to business users

• Experience with Microsoft Fabric, Databricks, or Power BI

• Experience with LLMOps practices including evaluation frameworks, prompt management, and model monitoring

• Familiarity with security, privacy, and compliance considerations for AI in regulated industries

• Consulting experience across multiple Clients or industries

• Anthropic training or certifications, or relevant Azure certifications

What Success Looks Like in This Role

• Claude solutions you build reach production and are used by real people, not just demoed

• Clients trust you as the engineer who knows how to make Claude work in their environment

• Your solutions are measured, documented, secure, and supportable after handoff

• You contribute MCP servers, Skills, and accelerators that make Collectiv's next Claude engagement faster

Why Collectiv

Join Collectiv for a rewarding career in a fully remote work environment with quarterly in-person team Experiences and competitive compensation. We provide a clear growth trajectory with professional development opportunities and a top-shelf benefits package. Enjoy unlimited time off and 100% covered health insurance, encompassing medical, dental, and vision plans for you and your family. Our comprehensive offerings, from a competitive 401(k) with a 4% match to educational assistance, tech stipend, and discounts on various goods and services, demonstrate our commitment to your well-being and success.

Collectiv is the leading boutique consulting and strategy firm specializing in Analytics, Planning, and AI with Power BI and the Microsoft data stack.

Our mission at Collectiv is simple: We help enterprises break free from stagnation and make better decisions.

Our Core Values:

• Growth Mindset: Bring solutions, not problems.

• Excel with Humility: Be humbly brilliant.

• Communicate Actively and Empathetically: Listen, ask, understand, help.

• Work Hard, Play Hard: Results are proportional to effort.

• Keep Calm and Carry On: Stay cool, calm, and Collectiv.

Originally posted on Himalayas