Senior AI Engineer

About Glass Lewis and Clarity AI
Founded in 2003, Glass Lewis is a leading global provider of independent, intelligence-focused corporate governance, stewardship, and proxy voting solutions. The firm serves more than 1,300 investment managers and pension funds globally, who use its high-quality corporate governance research and proxy voting software to carry out their fiduciary duties. Glass Lewis also helps companies understand corporate governance best practices and how investors view them. Headquartered in San Francisco, Glass Lewis has offices in North America, the United Kingdom, Europe, Asia, and Australia.

In September 2026, Glass Lewis and Clarity AI joined forces to integrate sustainability, governance and stewardship. Glass Lewis looks for people who take ownership, act with integrity, remain curious, and make thoughtful decisions that build trust with clients and colleagues. To learn more, visit https://www.glasslewis.com/.

About the role
We are looking for a Senior AI Engineer to build and operate production LLM and agent systems that deliver transparent, accurate sustainability data to our customers. You will join the Data Science team, working side by side with data scientists and other AI engineers to take pipelines from prototype to production and keep them reliable, observable and affordable at scale.
We build AI systems, from LLM pipelines and information extraction to agentic workflows, that turn large volumes of unstructured data into structured, reliable insights. Everything we ship has to be traceable to its sources and measurably correct, because investors rely on it. In this role you will own these systems end to end, from design and evaluation to deployment and monitoring, and collaborate across teams to translate business needs into scalable solutions.

Qualifications and Role-Specific Skills ​

• 3+ years of industry experience as an ML or AI engineer, including hands-on work shipping LLM-based or agentic systems.
• Strong Python, software engineering and system design expertise: maintainable architecture, testing and trade-offs such as latency vs cost or microservices vs monoliths.
• Hands-on experience building and evaluating LLM applications and agents (e.g., LangGraph, LangChain or similar), from tool calling, control flow and guardrails to evaluation architectures with labelled datasets, LLM-as-a-judge and robust metrics.
• Experience extracting information from unstructured data: document processing, OCR, retrieval systems.
• A product-oriented mindset and an interest in building products that solve real business problems.
• Experience running AI services in production on the cloud: serving, async processing, containers, CI/CD, observability, cost control and model routing.
• Experience using AI coding assistants and agents to work more efficiently, while keeping a critical eye on what they produce.
• University degree in CS/EE/STEM or related field.
• Self-starter who takes ownership, makes decisions with incomplete information, and cares deeply about sustainability and impact.
• Excellent oral and written English communication skills (minimum C1 level-proficient user).

Nice to have ​

• 5+ years of experience as an ML or AI engineer.
• MSc/PhD degree in CS/EE/STEM or related field.
• Experience working in a product-based company.
• Background in statistical modelling and classical machine learning, beyond LLMs.
• Experience with Kubernetes and AWS.
• Data engineering experience: SQL, data warehouses (e.g., Snowflake) and orchestration (e.g., Airflow).
• Experience with fintech/data products or sustainability/ESG domains.
• Experience working in cross-disciplinary teams with data scientists, product managers and domain experts.

• Translating methodology and business requirements into technical designs, together with data scientists and domain experts.
• Designing and building agentic systems in production: agent architecture, tool use, structured outputs, and the services that expose them.
• Developing and maintaining multi-step LLM pipelines that retrieve, extract and structure information from web and document sources into validated, production-ready data.
• Designing and building the evaluation architecture for our AI systems: golden datasets, LLM-as-a-judge, automated checks and regression tests that account for LLM non-determinism, so every change is backed by measured results.
• Making informed trade-offs between quality, latency and cost when choosing models, external providers, retrieval strategies and caching.
• Making the systems you build reliable in production: async and distributed execution, retries and rate limits, logging, tracing and alerting, and CI/CD.
• Acting as a link between project work and the AI Platform team: identifying shared needs, gaps and improvements across projects and feeding them back into the platform.
• Raising engineering standards through code review, testing and pair programming, and helping data scientists bring their work to production.
• Following developments in the field (new models, MCP, agent frameworks) and bringing the ones worth adopting into production.

Our tech stack is documented here: https://stackshare.io/clarity-ai