Senior LLM Systems Engineer — Production ML Orchestration

Dow Jones; New York (NY); On-site; USD 125,000 - 155,000; Full time

Benefits offered by this job

Comprehensive Healthcare Plans

Paid Time Off

Retirement Plans

Comprehensive Insurance Plans

Job summary

Dow Jones is seeking a Senior Machine Learning Engineer to design and build the core systems behind our LLM applications. You will craft the orchestration layer, reusable tooling, and evaluation harness to keep production AI trustworthy and efficient.

This role reports to the Director, Data Science & Insights. You will lead the development of multistep LLM workflows, integrate retrieval systems, and implement monitoring for accuracy, latency, and cost while mentoring teammates and setting

Qualifications

• At least 2+ years’ experience in software/ML engineering, including at least 1 year building LLM systems in production.
• Expert Python, hands on with LLM APIs and cloud platforms (AWS, Snowflake, Vertex).
• Deep experience orchestrating multistep LLM workflows as execution graphs (e.g. LangChain/LangGraph).
• Experience building agent harnesses: memory compression, skill disclosure, and tool design.
• Strong prompt engineering: tuning, versioning, and evaluation of prompts and model configs.
• A proven track record in AI evaluation, observability, and retrieval over enterprise data.
• Ability to explain complex AI concepts and tradeoffs clearly to nontechnical stakeholders.
• Fluency with agentic coding tools (e.g. Claude Code) and their architecture patterns.

Responsibilities

• Design and build the orchestration, prompting, and workflow layers behind production AI features
• Create composable tools and integrations, including retrieval and MCP servers and clients
• Build evaluators, dashboards, and alerts that track accuracy, latency, cost, and hallucination
• Harden the platform for production scale: caching, reliability, incidents, and model rollbacks
• Set the technical bar through architecture decisions, design reviews, and mentoring

Skills

Python

LLM APIs

Prompt engineering

Observability

Retrieval

Explain AI concepts

Agent tooling

LangChain

LangGraph

Claude Code

AWS

Snowflake

Vertex

Tools

LangChain

LangGraph

Claude Code

AWS

Snowflake

Vertex

Job description

Dow Jones is seeking a Senior Machine Learning Engineer to design and build the core systems behind our LLM applications. You will craft the orchestration layer, reusable tooling, and evaluation harness to keep production AI trustworthy and efficient.

This role reports to the Director, Data Science & Insights. You will lead the development of multistep LLM workflows, integrate retrieval systems, and implement monitoring for accuracy, latency, and cost while mentoring teammates and setting