About the position
As one of the first pioneers of earned wage access, our passion at EarnIn is building products that deliver real-time financial flexibility for those with the unique needs of living paycheck to paycheck. Our community members access their earnings as they earn them, with options to spend, save, and grow their money without mandatory fees, interest rates, or credit checks. We’re fortunate to have an incredibly experienced leadership team, combined with world-class funding partners like A16Z, Matrix Partners, DST, Ribbit Capital, and a very healthy core business with a tremendous runway. We’re growing fast and are excited to continue bringing world-class talent onboard to help shape the next chapter of our growth journey. We’re seeking a Python backend engineer with at least 2 years of experience to join our AI/LLM platform team. You’ll help build, deploy, and evaluate agentic systems—applications that use large language models (LLMs) to autonomously reason and act in user-facing workflows. Your work will support EarnIn’s mission to provide fair and intelligent financial tools to millions of users.
Responsibilities
- Build backend services in Python to support agentic applications powered by LLMs.
- Design and implement prompt orchestration layers, memory/context pipelines, and external tool integrations used by agents.
- Develop systems for evaluating agent behavior, including success metrics, error tracing, and regression testing of multi-step workflows.
- Expose and maintain RESTful APIs that interact with internal tools and external-facing LLM applications.
- Collaborate cross-functionally with ML engineers, data scientists, and product to shape intelligent and safe AI features.
- Manage observability for agent pipelines, using tools like logging, tracing, and distributed monitoring.
- Build and maintain asynchronous processing systems (e.g., Celery, asyncio, or messaging queues).
Requirements
- Bachelor's or Master’s degree in Computer Science, Engineering, or a related field.
- 2+ years of industry software engineering experience.
- Strong understanding of LLM APIs (e.g. OpenAI, Claude) and prompt engineering.
- Experience developing or integrating with agentic systems (e.g., LangChain, custom frameworks).
- Familiarity with designing evaluation frameworks for AI behavior, including automated checks and offline test harnesses.
- Experience with API design, async workflows, and production database usage (SQL or NoSQL).
- Clear communication and collaborative mindset.
Nice-to-haves
- Experience with LLM evaluation tooling, prompt unit testing, or behavioral regression suites.
- Familiarity with vector stores (e.g., Weaviate, Pinecone, Qdrant).
- Knowledge of OpenTelemetry or similar observability frameworks for distributed systems.
- Exposure to container-based deployment or serverless environments (Docker, AWS Lambda, etc.).
Benefits
- Base salary range of $169,800 - $207,600 plus equity and benefits.
- Hybrid position requiring in-office work 2 days a week.
