Machine learning Engineer
Explicitly rejects vibe coding and emphasizes spec-driven development and disciplined workflows to avoid unstructured coding.
About the Role
Machine Learning Engineer focused on designing, building, and deploying agentic systems using modern agent platforms and SDKs. The role emphasizes disciplined development workflows, spec-driven development, cross-functional collaboration, and hands-on LLM tooling to create reliable, production-grade agents.
Job Description
Role
We are seeking a Machine Learning Engineer with deep experience in agentic platforms to design, build, and deploy production agents. The role requires hands-on work with agent SDKs/frameworks, creating interaction patterns between agents, tools, and users, and driving adoption of structured development practices across teams.
Key Responsibilities
- Build and deploy agents using platforms such as AgentCore, Gemini Enterprise, and Azure Copilot.
- Design agent interaction patterns and manage agent communication, memory, and context.
- Implement and maintain LLM tooling including Cursor commands, Claude skills, steering documents, and CI agents.
- Apply and advocate spec-driven development and strong development workflow practices (branching, code review, CI/CD, testing, observability).
- Collaborate cross-functionally with engineers, product managers, and stakeholders to define clear requirements.
- Run workshops, training sessions, and demos to drive adoption and teach best practices.
- Experiment with and standardize new agent workflows and tooling for team-wide use.
Requirements
- Deep, hands-on experience building and deploying agents on agentic platforms.
- Strong familiarity with agent SDKs and frameworks such as ADK, LangChain, and Strands.
- Solid development workflow discipline: branching, code review, CI/CD, testing, and observability.
- Understanding of agentic patterns and protocols (A2A, MCP, RAG), memory and context management.
- Experience creating and maintaining Cursor commands, Claude skills, steering documents, or similar LLM tooling.
- Ability to work cross-functionally and lead training/workshops to drive adoption.
- Clear understanding of the limitations of “vibe coding” and preference for structured/spec-driven approaches.
Nice to have
- Experience with enterprise AI governance, safety, and compliance.
- Background in developer experience (DevEx), platform engineering, or internal tools.
- Familiarity with observability and monitoring for agents (traces, logs, evaluation frameworks, feedback loops).
- Experience integrating agents with existing systems via APIs, webhooks, and event-driven architectures.
Tools & Technologies
Agent platforms and SDKs explicitly used or referenced include: AgentCore, Gemini Enterprise, Azure Copilot, ADK, LangChain, Strands, Cursor, and Claude. Work will involve CI/CD practices and integrations via APIs/webhooks and event-driven architectures.