1. Introduction to the Position

The Developer Productivity Engineering team at MX is redefining how software is built, tested, and operated by embedding AI directly into the developer experience. Our mission is to enable engineers to move faster with higher confidence by providing intelligent platforms, automation, and self-service capabilities.

We are at an inflection point where AI is transforming software development - from code generation and reviews to autonomous agents executing complex workflows. This role sits at the heart of that transformation.

You will be responsible for building and operationalizing foundational platforms such as an LLM Gateway and Agentic Workflow Platform that enable teams across MX to safely and efficiently adopt AI in their development lifecycle.

From powering AI-assisted code reviews to enabling every engineer at the company to integrate sophisticated AI into their workflows safely, reliably, and at scale, your work will directly amplify engineering velocity and innovation across the organization.

If you are excited about building scalable platforms, shaping the future of AI-driven development, and solving complex distributed systems problems - this is your opportunity to have outsized impact.

2. Job Responsibilities

Build AI Developer Platforms and integration across SDLC:
Design and build core AI developer platforms, like an LLM Gateway for standardized LLM access (routing, caching, observability, cost control), and integrate AI features (code generation, reviews, testing, debugging, documentation) across the SDLC.
Enable Agentic Systems:
Build frameworks and orchestration layers to enable developers to create, deploy, and operate agent-based workflows (multi-step reasoning systems, Harnesses, tool-using agents, etc.).
Developer Experience & Productivity:
Create intuitive abstractions, SDKs, and APIs that reduce friction and enable self-service adoption of AI capabilities across teams.
Scalable Platform Architecture:
Architect and operate highly scalable, low-latency backend systems for high-throughput AI workloads, establishing best practices and golden paths for AI application development.
Observability & Governance:
Implement monitoring, tracing, evaluation pipelines, and guardrails for AI systems, including prompt/version management, response quality tracking, and safety controls.
Cost & Performance Optimization:
Design systems to optimize latency, throughput, and cost of LLM usage through techniques like caching, batching, and model routing strategies.
Collaboration:
Work closely with platform, SRE, security, and product engineering teams to ensure AI capabilities are reliable, secure, and aligned with business needs.

3. Basic Qualifications

8+ years of experience in software engineering, backend development, or platform engineering.
Experience working with LLMs and Agentic AI systems, including Context engineering, Harness engineering, evaluation, or model integration.
Strong programming experience in languages such as Golang, Java, or Python.
Experience building and operating distributed systems and scalable backend services.
Experience designing and consuming APIs, microservices, and event-driven architectures.
Familiarity with CI/CD pipelines, testing frameworks, and developer tooling.
Strong debugging and problem-solving skills in production environments.

4. Preferred Qualifications

Experience building or integrating LLM Gateways, AI SDKs, or internal AI platforms.
Familiarity with agent frameworks (e.g., ADK, LangGraph, LangChain, or similar orchestration systems).
Experience designing multi-step workflows or automation systems using AI.
Knowledge of vector databases, embeddings, and retrieval-augmented generation (RAG) systems.
Experience with observability for AI systems, including prompt/version tracking and evaluation pipelines.
Understanding of cost optimization strategies for large-scale AI workloads.
Experience building developer platforms or internal tools that improve engineering productivity.
Exposure to SRE practices, including reliability, SLIs/SLOs, and incident response.
Hands-on experience with cloud platforms (AWS preferred) and containerized environments (Kubernetes).

5. Impact

Accelerate engineering velocity across MX by embedding AI into everyday engineering workflows.
Enable safe, scalable adoption of AI across the organization.
Reduce cognitive load on developers through intelligent automation and tooling.
Lay the foundation for autonomous and semi-autonomous engineering systems.

Senior Software Engineer - AI Platforms

Senior Software Engineer - AI Platforms