About the Role
Join our engineering team at the forefront of applied AI to design and build production-grade ML features that power the core product experience. You'll shape the future of how our platform leverages large language models, retrieval-augmented generation, and intelligent automation — working across the full lifecycle from rapid prototyping to reliable, scalable production systems.
What You'll Do
- Design and implement LLM-powered features and intelligent workflows that solve real customer problems
- Build and optimize retrieval-augmented generation (RAG) pipelines including document ingestion, chunking strategies, embedding models, and vector search
- Develop and refine prompt engineering strategies across multiple foundation models and use cases
- Create evaluation frameworks and benchmarking infrastructure to systematically measure model performance, accuracy, and cost-effectiveness
- Implement guardrails, output validation, and safety filtering to ensure reliable and trustworthy AI behavior in production
- Monitor and optimize token usage, latency, and inference costs across multi-model architectures
- Collaborate closely with product and engineering teams to identify high-impact AI opportunities and translate them into shipped features
Requirements
- 3+ years of experience in machine learning or AI engineering, with hands-on experience building LLM-powered applications
- Strong proficiency in Python with production-level software engineering practices
- Experience building RAG systems with vector databases (Pinecone, Weaviate, pgvector, or similar) and document processing pipelines
- Solid understanding of NLP fundamentals, prompt engineering, function calling, and tool-use patterns
- Familiarity with LLM orchestration frameworks such as LangChain, LlamaIndex, or equivalent
- Experience with cloud platforms (AWS, Azure, or GCP) for deploying and scaling ML workloads
- Ability to design evaluation criteria and measure AI output quality systematically
Nice to Have
- Experience building AI systems in regulated, high-security, or compliance-driven environments
- Background in MLOps — model versioning, experiment tracking, CI/CD for ML pipelines
- Hands-on experience fine-tuning or distilling open-source models (LLaMA, Mistral, etc.)
- Experience with multi-agent frameworks, autonomous agent architectures, or tool-use orchestration
- Published research or technical writing in NLP, information retrieval, or applied ML