CareerPlanGet AI match score →

Staff Software Engineer

💼 Full-time🗓 2026-06-24 → 2026-06-25

Core

Own core AI-powered product features end-to-end, designing and optimizing production LLM systems including RAG pipelines, AI agents, and fine-tuning to directly impact revenue and retention.

Role type

Staff Software Engineer (Hands-on IC)

Builds

Production LLM systems, AI agents, RAG pipelines, embedding workflows, and evaluation frameworks.

Domain

Generative AI / Large Language Models / Content Automation

Deliverable

production ML models

Required skills

Python, System Design, API Design, SQL, Vector Databases, Cloud Infrastructure, LLM Architecture, RAG Pipelines, AI Agents, Fine-tuning, Business-First Thinking

Preferred skills

Open-source contributions, Technical blogging, GEO experience

Technologies

Python, SQL, Vector Databases, Cloud Infrastructure

Responsibilities

Design and build production LLM systems including RAG pipelines and AI agents; Make architecture decisions across backend services and databases; Connect engineering decisions to user outcomes and revenue metrics; Collaborate with founders to define solutions for vague high-impact problems.

Seniority

Staff, hands-on IC

Rewrite
## About the Role We're hiring a strong senior IC engineer to own core projects at Writesonic. This is not a management position—it's a hands-on builder role for someone who can go deep into hard problems, ship fast, and think like a product owner from an overall business, use-case, and customer perspective. You will take vague, high-impact problems and turn them into production systems that directly move revenue and retention. You'll work across LLM infrastructure, product features, and AI tooling—operating with full autonomy and minimal hand-holding. ## Responsibilities - Own and ship core AI-powered product features end-to-end—from problem definition to production deployment and measurement. - Design, build, and optimize production LLM systems including RAG pipelines, AI agents, embedding workflows, evaluation frameworks, and fine-tuning pipelines. - Make architecture and system design decisions across backend services, databases (SQL and vector), APIs, and cloud infrastructure. - Dive deep into the business domain (marketing, SEO, GEO, content automation) to make smart product and engineering trade-offs. - Connect every engineering decision to user outcomes—ask "does this move revenue or retention?" before "is this technically elegant?" - Collaborate directly with founders and cross-functional teams, operating as a product-minded engineer rather than a spec-follower. ## Requirements ### Backend Engineering Fundamentals - Strong proficiency in Python as the primary language. - Solid grasp of system design, API design, SQL and vector databases, and cloud infrastructure. ### Production LLM Experience (2+ Years) - Built and shipped real production systems using LLMs, RAG pipelines, agents, embeddings, evals, or fine-tuning. - Understands the limits of models—not just the hype. Can clearly articulate the difference between RAG and fine-tuning and when to use each. ### Independent Ownership - Can take a vague problem, define the solution, build it, and measure its impact without hand-holding. - Track record of shipping autonomously and iterating based on real user/business feedback. ### Domain-Diving Instinct - Willingness and ability to learn the business domain (marketing, SEO, GEO, content) deeply enough to make smart product calls. - This is the rarest trait we screen for—engineers who understand the "why" behind what they build. ### Business-First Thinking - Consistently connects engineering decisions to user outcomes, revenue impact, and retention metrics. - Asks "does this move the needle for customers?" before optimizing for technical elegance. ## Nice to Have - Open-source contributions or a published technical blog demonstrating depth of thinking. - Experience with GEO
Sourced via wellfound · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
Apply on Wellfound ↗