AI Content Engineer

LlamaIndex; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

LlamaIndex in San Francisco seeks a highly technical ML engineer to produce authentic technical content at high velocity, combining document AI expertise with strong writing skills. You will build benchmarks, publish analyses, and help position us as the leader in document understanding.

This role is hands-on: you will write real code, run experiments, and translate work into published content at a pace faster than academic publishing.

Qualifications

• Experience in software engineering with ML focus and production Python
• Ability to write clearly and quickly about technical topics
• Ability to ship; publish at blog pace
• Experience reading and synthesizing research papers rapidly
• Self-directed and able to identify compelling topics
• Track record of high-velocity output in fast-paced teams

Responsibilities

• Design, build, and maintain comprehensive benchmarks for document parsing and understanding
• Publish high-quality technical content at a weekly cadence (blog posts, benchmark reports, technical comparisons, tutorials)
• Stay deeply current with the document AI landscape - new models, papers, competitors, techniques
• Run experiments and translate findings into publishable artifacts quickly
• Produce technical analyses that demonstrate our capabilities against alternatives
• Contribute to open-source examples, notebooks, and documentation
• Collaborate with the core ML team to surface improvements and capabilities worth highlighting
• Engage authentically with the developer community through technical content (not conferences/events)

Skills

Production Python

ML engineering

Software engineering fundamentals

Research synthesis

High-velocity output

Self-directed

Technical writing

Tools

Benchmarks tooling

Open‑source notebooks

Job description

Join us and help shape the future of AI by defining the narrative around document understanding.

About the Role

We are seeking a highly technical ML engineer who can produce compelling, authentic technical content at high velocity. You will combine deep expertise in document AI with strong writing skills to build benchmarks, publish technical analyses, and establish our position as the definitive leader in document understanding.

This is not a traditional DevRel or Marketing role. You will write real code, build real benchmarks, and run real experiments - then translate that work into published content at a pace far faster than academic publishing. Your output will directly drive awareness and adoption among the developers building the next generation of document-powered applications.

Responsibilities

• Design, build, and maintain comprehensive benchmarks for document parsing and understanding


• Publish high-quality technical content at a weekly cadence (blog posts, benchmark reports, technical comparisons, tutorials)


• Stay deeply current with the document AI landscape - new models, papers, competitors, techniques


• Run experiments and translate findings into publishable artifacts quickly


• Produce technical analyses that demonstrate our capabilities against alternatives


• Contribute to open-source examples, notebooks, and documentation


• Collaborate with the core ML team to surface improvements and capabilities worth highlighting


• Engage authentically with the developer community through technical content (not conferences/events)

Required Qualifications

• Experience in software engineering (ML engineering + research a bonus)


• Strong software engineering fundamentals with production Python experience


• Understanding of modern ML techniques, particularly in computer vision, NLP, or multimodal learning


• Demonstrated ability to write clearly, quickly, and authentically about technical topics


• Bias toward shipping - comfortable publishing at blog pace, not paper pace


• Ability to read, understand, and synthesize research papers rapidly


• Scrappy and self-directed - can identify what's worth writing about and execute end-to-end


• Track record of high-velocity output in fast-paced environments

Preferred Qualifications

• Experience with vision-language models, transformer architectures, or document AI specifically


• Existing portfolio of technical writing (blog posts, tutorials, technical documentation)


• Experience building evaluation frameworks or benchmarks


• Familiarity with OCR, layout analysis, table extraction, or document structure understanding


• Active presence in ML/AI technical communities


• Experience with LLM applications and RAG systems

Location

In-person in San Francisco.

Why Join Us?

Shape the Narrative: Your content will define how developers think about document understanding. You'll have direct influence on market perception.

Technical Credibility: Work with cutting-edge document AI systems processing millions of documents. Your benchmarks and analyses will be grounded in real capabilities.

High Autonomy: Significant freedom to identify what matters and publish quickly. No lengthy approval chains.

Growth Opportunity: Help build this function from the ground up as we scale.

Pursuant to the SanFrancisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.