Gen AI Software Engineer

About the role

We are looking for a mid-level AI Engineer to take ownership of end-to-end AI feature development and play a key role in shaping the architecture and design of our AI solutions. In this role, you will build and deploy production-grade LLM applications, advanced RAG pipelines, and agentic workflows integrated with our AWS and Snowflake data platform. You'll collaborate closely with data engineers, solution architects, and business stakeholders to deliver scalable, high-impact AI capabilities that solve real-world business challenges.

About Verisk

Verisk is a global leader in data analytics and risk assessment, serving customers across the insurance, healthcare, financial services, and supply chain industries. As a publicly traded company with a strong global presence, we continue to expand into new markets while investing in innovation and long-term growth.

• Own end-to-end delivery of AI features and integrations — from requirements through to deployed, monitored solutions.

• Design and implement advanced RAG pipelines including chunking strategy, retrieval architecture, hybrid search, and evaluation frameworks (RAGAs, LangSmith).

• Build adaptive agentic workflows and multi-step AI systems using frameworks such as LangChain, LlamaIndex, LangGraph, or AutoGen.

• Develop and maintain MCP servers and integrations connecting AI models to Snowflake, AWS services, and enterprise APIs.

• Integrate AI capabilities with our AWS data platform — S3, SageMaker, Lambda, Bedrock — and surface insights through ThoughtSpot.

• Contribute to technical design discussions, proposing scalable, secure, and cost-efficient architectural patterns.

• Evaluate AI model outputs systematically; own optimization of cost, latency, and quality metrics.

• Apply AI governance practices — PII handling, data access controls, and prompt injection mitigations.

• Translate business requirements into technical specifications in collaboration with subject matter experts and project managers.

• Conduct and participate in code reviews; actively support the growth of junior engineers.

You will work within the following core technology environment:

• Cloud Platform: AWS (S3, EC2, Lambda, SageMaker, Bedrock, IAM)

• Data Warehouse: Snowflake (Snowpark, virtual warehouses, stages, streams)

• Analytics & BI: ThoughtSpot

• Search & Vector: OpenSearch, pgvector (Postgres)

• LLM Providers: OpenAI, Anthropic / Claude, AWS Bedrock

• AI Connectivity: Model Context Protocol (MCP) servers and integrations

• Version Control & Project Tooling: Bitbucket, Jira, Confluence

• Dev Tooling: Docker, Python, AI coding assistants (Cursor, GitHub Copilot, Claude Code)

Education, experience & technical skills:

• Bachelor's degree (or higher) in Computer Science, AI, Data Science, or a related field.
• 2–4 years of hands-on experience in software or AI engineering, with a proven track record of delivering AI/ML solutions.
• Strong Python skills, including pytest, async programming, type hints, packaging, and code reviews, with experience building production services.
• Experience designing and deploying end-to-end RAG pipelines using OpenSearch, pgvector, reranking, and evaluation frameworks.
• Hands-on experience building agentic AI workflows, including tool-use agents and human-in-the-loop patterns.
• Experience with MCP integrations connecting AI applications to Snowflake, REST APIs, and enterprise systems.
• Familiarity with AI evaluation, model observability, prompt security, and guardrails across OpenAI, Anthropic, and Amazon Bedrock.
• Experience deploying AI solutions on AWS (S3, Lambda, SageMaker, ECR, IAM).
• Working knowledge of Snowflake, including Snowpark and core platform features.
• Experience with Docker, REST APIs, CI/CD, and AWS deployment pipelines.
• Understanding of data security, PII handling, and responsible AI practices.

Soft skills: