Design and own the AI infrastructure: private model deployment (on-premise or isolated cloud),
data pipelines, vector stores, and serving infrastructure - ensuring no sensitive data leaves our
controlled environment.
Build AI capabilities into our applications.
Automate internal workflows currently done manually, using LLM-based agents and process
orchestration.
Establish evaluation frameworks (evals) to measure quality, reliability, and latency of AI features
before and after deployment.
Define AI engineering standards, tooling choices, and best practices that the broader team will
build on.
Requirements: 4+ years of software engineering experience, with 2+ years building and shipping LLM-based
systems in production.
Experience deploying AI/LLM workloads in privacy-sensitive or regulated environments.
Hands-on experience with RAG architectures: document ingestion, chunking, embedding, and
retrieval using vector databases (pgvector, Weaviate, Qdrant, etc.).
Experience building and orchestrating LLM agents for multi-step task automation (LangGraph,
CrewAI, custom implementations).
Strong Python skills; solid understanding of system design, APIs, and data architecture.
Ability to own architectural decisions - evaluate tools, make build-vs-buy tradeoffs, and set
technical direction independently.
Excellent communication skills - able to translate AI capabilities into concrete business value for
non-technical stakeholders.
This position is open to all candidates.