AI/ML Engineer

About the role

We're shipping LLM-backed features into client products every month — agent workflows, RAG systems, document understanding, automation pipelines. We need an engineer who can take a fuzzy problem statement and turn it into a working, observable, cost-controlled system in production.

What you'll do

• Build and productionize LLM features (retrieval-augmented generation, agents, classification)
• Design evaluation suites that catch regressions before they hit users
• Work with engineering teams to integrate AI features into existing products
• Optimize cost and latency across the LLM and vector-search stack
• Stay current on the rapidly evolving model landscape and translate it into practical advice
• Document tradeoffs clearly so non-AI engineers can extend your work

What we're looking for

• 3+ years of ML or AI engineering experience, including time in production
• Hands-on experience with the OpenAI / Anthropic / open-source LLM ecosystems
• Strong Python and at least one of TypeScript / Go for systems integration
• Experience with vector databases (Pinecone, Weaviate, pgvector)
• Practical understanding of where ML helps and where it doesn't
• Ability to communicate AI tradeoffs to non-technical stakeholders

Nice to have

• PyTorch or fine-tuning experience
• Background in data engineering or MLOps
• Published research or strong open-source presence
• Experience with multi-agent or tool-using AI systems

Tech you'll work with