Role overview
We are seeking a **Software Engineer, AI** to build and scale cutting-edge AI features from the ground up. You will report directly to the Founder and CEO and play a pivotal role in defining how AI transforms our product, rapidly iterating based on customer feedback and pushing the boundaries of what's possible with LLMs.
**What you will do - ship AI features end-to-end:**
* **Build the next generation of AI features** at AutoAssist, owning the full lifecycle from conception to production
* **Develop AI infrastructure** that powers AutoAssist's features - prompt execution engines, search infrastructure, and orchestration layers
* **Improve LLM observability** - design and implement AI evals (online and offline), scorers, and monitoring systems to set up AutoAssist's AI for the next wave of scaling
* **Enhance quality and performance** of AI features through systematic testing, optimization, and real-world iteration
* **Architect AI-native workflows** with intelligent automation and multi-agent orchestration
* **Integrate complex AI systems** - LLM APIs, vector databases, embedding pipelines, and retrieval augmented generation (RAG)
* **Build analytics and intelligence layers** that surface insights from AI-generated data
**What we're looking for:**
* 3+ years building production software with strong engineering fundamentals
* Experience with AI/ML integration, LLM APIs, RAG architectures, and prompt engineering
* Full-stack or backend expertise with modern tech stacks (we use React, Golang, Python, GraphQL, and AWS)
* Proficiency in Python for AI/ML workflows - model integration, data pipelines, or ML tooling
* Track record of shipping code efficiently and iterating rapidly based on user feedback
* Autonomy-driven mindset - you thrive when you own the details and project manage your own work
* You dislike meetings and would much rather focus your time on building, being productive, and shipping code
* Self-aware about your strengths - you know what you're great at and what you're less great at, and you play to your strengths
* Comfortable with ambiguity and building in a fast-paced, early-stage environment
**Preferred Qualifications:**
* Experience with Next.js, TypeScript/Node.js (Bun), T3 Stack, tRPC, Prisma
* Background in LLM fine-tuning, evaluation frameworks, or AI observability tools
* Familiarity with Python AI/ML libraries (LangChain, LlamaIndex, OpenAI SDK, Hugging Face, PyTorch)
* Experience with vector databases (Pinecone, Weaviate, pgvector) and embedding models
* Familiarity with AI-assisted development tools (Cursor, Copilot, Lovable)
* B2B SaaS or enterprise product development
* Multi-tenant architecture and API design
**Why this matters:**
* Direct impact on AI product strategy and technical direction
* AI-first architecture from day one - no legacy constraints
* Opportunity to build in a massive, underserved market where AI can be truly transformative
* Ship features that reach users quickly and iterate based on real feedback
**Don't think you meet all the qualifications? Apply anyway. We'd love to hear what excites you about building AI-native products.**
Job Type: Full-time
Pay: $95,000.00 - $150,000.00 per year
Ability to Commute:
* West Chester, PA 19382 (Required)
Work Location: Hybrid remote in West Chester, PA 19382