About the Role

We're looking for an AI Engineer who can turn product problems into working AI features. You'll design, build, and ship systems powered by modern language models, working directly with product and engineering teams to get solutions into production.

Key Responsibilities

• Design and implement AI-powered features (agents, chat, retrieval, summarization, automation)

• Integrate LLM providers (OpenAI, Anthropic) into existing services

• Build and maintain pipelines for prompts, evaluation, logging, and observability

• Optimize for latency, cost, and reliability in production

• Collaborate with cross-functional teams on end-to-end solutions

• Write clean, maintainable code with tests and documentation

What We're Looking For

• 3+ years professional software engineering experience

• Strong coding skills in Python, TypeScript, or JavaScript

• Hands-on experience building real AI-powered features (LLM apps, RAG, agents)

• Good understanding of language models, embeddings, vector stores, and prompt design

• Experience with APIs (REST/GraphQL) and cloud platforms

• Strong communication skills and ability to work with technical and non-technical stakeholders

Nice to Have

• Experience with LangGraph or agent frameworks

• Familiarity with vector databases (Pinecone, Weaviate, pgvector)

• Background in startups or fast-paced environments

• Data science or ML background