Deep experience building production applications with LLM frameworks such as LangChain, LangGraph or LlamaIndex.
Hands-on expertise with vector databases (Pinecone, Weaviate, PostgreSQL) and search algorithms.
Strong understanding of LLMOps principles, including model registry, versioning, and serving infrastructure specifically in Google Cloud.
Nice to have: Experience in Typescript development for prototyping and integrations
Nice to have: Proficiency with git workflows and understanding of standard application development processes
Preferred Qualifications
Knowledge of advanced prompt engineering and fine-tuning techniques (LoRA, PEFT).
Experience optimizing inference costs and latency for large-scale deployments.
Previous experience in a client-facing consulting role, managing diverse stakeholders and navigating complex organizational structures.
Any Google Cloud Professional Certification
What you’ll be doing in this role
Lead the implementation of rigorous evaluation frameworks to monitor model performance, drift, and cost in real-time.
Architect and develop high-performance backend services and APIs using Python (FastAPI) to serve large language models at scale.
Design advanced Retrieval-Augmented Generation (RAG) systems, selecting and managing vector databases and optimizing embedding strategies for accuracy and speed.
Establish comprehensive model observability and guardrail systems to monitor real-time performance, detect distribution drift, and implement automated safety filters that mitigate hallucinations, bias, and toxic outputs in production environments.
Build robust integration layers that connect AI agents securely to external enterprise systems, CRMs, and legacy databases.
Conduct code reviews, provide technical guidance, and foster a culture of continuous learning and innovation within the engineering team.
Collaborate with infrastructure teams to define deployment strategies, ensuring solutions scale dynamically under load.
Define the end-to-end architecture for AI products on cloud platforms (preferably Google Cloud Platform), ensuring high availability, security, and cost-effectiveness.
What you’ll need to accomplish in your first year
Develop reusable internal libraries and architectural patterns and standards to accelerate the delivery of AI solutions across multiple client engagements.
Mentor engineers on best practices for building deterministic software around probabilistic AI models.
Our total rewards program is designed for your protection, peace of mind, and overall well-being. In addition to our outstanding basics, we offer a net-zero cost medical option, company contributions to your HSA, fertility support, fully-paid parental leave, a monthly stipend for your lifestyle spending account, and much more.
Apply today or check out all our opportunities!
#LI-Remote
#LI-Hybrid
#LI-Onsite
By submitting your application, you consent to our collection, processing and disclosure of the contained personal data in accordance with our data practices. If you are a resident of the U.S. state of California, you can read about our data practices and your related privacy rights here. If you are a resident of the European Economic Area, Switzerland or the United Kingdom, you can read about our data practices and your related privacy rights here.