Lead GenAI Engineer

You might be our missing piece if you have:

• Strong Python skills and a solid foundation in software engineering—clean architecture, version control, readable code, and good engineering judgment.

• Experience building and shipping production-grade backend applications with FastAPI, Flask, or Django.

• A proven track record of designing and scaling ML and/or GenAI systems in production, from data pipelines and deployment to monitoring, optimization, and evaluation.

• Hands-on experience with GenAI frameworks such as LangChain, LangGraph, ADK, or Haystack.

• A good understanding of commercial LLM APIs (such as OpenAI, Anthropic, and similar providers), including where they shine, where they fall short, and how to work with those trade-offs.

• Strong experience with RAG systems, including embeddings, vector search, document retrieval, chunking strategies, reranking, and context construction.

• Experience designing AI-powered product architectures, including multi-agent systems, tool-using agents, orchestration flows, and inference architectures.

• A solid understanding of agentic workflows—planning, memory, tool use, handoffs, and how to make multi-step systems work reliably in practice.

• Experience defining and implementing evaluation strategies for GenAI systems, covering retrieval quality, answer quality, task success, latency, cost, and hallucination tracking.

• Comfort working with relational and non-relational databases, as well as vector stores, and a good understanding of how data should be modeled and prepared for ML and GenAI use cases.

• Strong hands-on knowledge of Docker and a practical understanding of containerized workflows. DevOps might own the pipelines, but you know how to work well with them.

• Experience building systems that are easy to debug and operate, with solid logging, tracing, monitoring, and observability practices.

• Good judgment around guardrails, privacy, and security when building AI systems that interact with sensitive data, users, or external tools.

• An interest in agentic coding and spec-driven development.

• Experience leading AI/ML initiatives from idea to production.

• A natural tendency to support and mentor others, helping them grow both technically and in the way they approach problems.

• Experience with traditional ML or Computer Vision systems that require model architecture design, feature engineering, and dataset management.
  

We would be thrilled if you have:

• Experience evaluating and improving agentic systems in real-world settings.

• Familiarity with prompt engineering and context engineering, and a feel for improving consistency, controllability, and tool-calling reliability.

• You have used or implemented MCP servers or clients.

• An eye for research and the ability to turn ideas from papers or experiments into production-ready solutions.

• Comfort working with cloud infrastructure such as AWS, Azure, GCP, or DigitalOcean, along with a good understanding of CI/CD practices.

• Hands-on experience with Databricks or Apache Spark.

• Experience with observability or evaluation tooling built specifically for LLM-based systems.

• The ability to work comfortably across product, engineering, and research, and help connect the dots between them.

• Experience with experiment tracking tools such as MLFlow.

• Experience with core ML frameworks such as PyTorch, Keras, or similar.

We will be working together on the following:

• Understanding client needs and shaping AI solutions that are practical, well-architected, and worth building.

• Designing and delivering agentic RAG systems that are reliable, measurable, and ready for production.

• Leading major AI initiatives from architecture design to delivery.

• Defining evaluation approaches and feedback loops for retrieval, generation, and agent behavior.

• Driving good engineering practices around reproducibility, monitoring, observability, scalability, and operational reliability.

• Helping shape the guardrails, security practices, and engineering standards behind the AI systems we build.

• Mentoring and supporting the AI team through pair programming, code reviews, and hands-on collaboration.

• Keeping a close eye on what is happening in the field and bringing in new ideas when they genuinely make sense.

• Using the latest AI-assisted engineering practices to build thoughtful, high-quality solutions.

• Continuously raising the bar for how we design, build, and deliver AI products.