Senior AI Engineer

Novisto; United States; Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

Stock options

Remote-friendly

4 weeks vacation

Summer hours

Job summary

Novisto is seeking a Senior AI Engineer to own the retrieval, orchestration, and AI workflow layers behind our knowledge-driven experiences. You will design and operate production systems that retrieve, rank, and assemble context for LLMs, and build extraction and agentic pipelines that turn documents into structured data.

You will work hands-on to ensure reliable, scalable deployments on Kubernetes, partnering with product and platform teams to raise AI quality into a measurable product

Qualifications

• 6+ years of software engineering experience.
• 2+ years building and scaling LLM-backed systems in production.
• Strong Python expertise and cloud infrastructure fundamentals.

Responsibilities

• Design and manage end-to-end Retrieval-Augmented Generation infrastructure.
• Develop agentic flows and tool/token management.
• Create document automation pipelines to extract structured data.
• Support API and infrastructure ownership with Kubernetes deployments.

Skills

Python

FastAPI

Cloud infrastructure

CI/CD

LLM integration

Vector databases

Tools

pgvector

Qdrant

Elasticsearch

LangGraph

Google ADK

Job description

As a Senior AI Engineer, you will own the layer that makes Novisto's products intelligent: the retrieval and orchestration systems behind our conversational and knowledge-driven experiences, and the automated AI workflows that turn documents into structured, usable data.

You will apply strong software engineering principles to design how our systems retrieve, rank, and assemble context for Large Language Models, build the extraction and agentic pipelines that replace manual data work, own the platform services that expose those capabilities to product teams, and set the engineering standards for how we build with AI. You'll partner closely with Tech Leads, Product Managers, Principal Devs, and Platform Engineering to turn AI quality into a measurable product advantage.

This is a hands-on senior engineering role focused on production systems, not a research position: you'll compose, orchestrate, and rigorously evaluate foundation and document-understanding services rather than develop models from scratch.

What you'll build and own

• RAG Architecture: Design and manage our end-to-end Retrieval-Augmented Generation infrastructure, including vector databases, hybrid search, chunking strategies, and prompt architecture.
• Develop Agentic Flows: Build agentic flows and agents, including state management, tool management, MCP server guardrails, and token management.
• Document Automation Pipelines: Create agentic workflows and extraction pipelines that pull structured facts from complex documents. You'll incorporate tool-calling, fallback logic, and human-in-the-loop review paths.
• LLMOps & Evaluation: Build systematic evaluation harnesses to track retrieval precision, extraction accuracy, and hallucination rates. Set up comprehensive observability for token spend, quality drift, and overall system health.
• API & Infrastructure Ownership: Drive senior-level software development by designing, building, and maintaining robust APIs. Understand DevOps best practices and manage scalable deployments utilizing Kubernetes.
• Technical Delivery: Contribute hands-on to the codebases making up the retrieval, extraction, and orchestration platform. Drive reliable, high-quality delivery through planning, code reviews, and pairing. Write technical tickets to bridge functional intent and execution, and collaborate with tech leads to ensure cross-team alignment.

Core Requirements

• Experience: 6+ years of software engineering experience, including 2+ years specifically building, operating, and scaling LLM-backed systems in production.
• Core Skills: Strong Python expertise (e.g., FastAPI) and solid fundamentals in cloud infrastructure (Azure/GCP), CI/CD, and modern architecture.
• AI/Search Tech: Hands-on experience with vector databases (pgvector, Qdrant, Elasticsearch, etc.), LLM provider APIs, and orchestration frameworks such as LangGraph or Google ADK.
• Applied AI Knowledge: Proven track record of owning production RAG systems, complex document extraction pipelines, and multi-step agentic workflows.
• Operational Mindset: Deep understanding of LLM versioning, rate limiting, cost control, and automated evaluation for non-deterministic systems.
• Bonus: Experience in ESG, data-intensive applications, or regulated SaaS.

What We Offer

• Impact: Advance Novisto's mission to drive economic, environmental, and social sustainability through better ESG data management.
• Compensation & Equity: Stock option plan in an early-stage, well-financed company.
• Flexibility & Time Off: Remote-friendly flexible schedules, 4 weeks of vacation, and summer hours.
• Health & Wellness: 100% insurance coverage and access to Dialogue's telemedicine app.