Job Description

Your mission

About StockStory

Index.dev is partnering with StockStory (CNBC / VERSANT) to hire a Senior AI Engineer in Prague.

VERSANT is an independent, publicly traded company that brings together powerhouse brands such as CNBC, MS NOW (formerly MSNBC), USA Network, Oxygen, E!, SYFY, and Golf Channel along with dynamic digital and direct-to-consumer brands such as Fandango, Rotten Tomatoes, GolfNow, GolfPass, and SportsEngine.

StockStory, now part of CNBC under VERSANT, is building the next generation of AI-powered equity research for individual investors. This is a chance to build products that can shape how millions of consumers understand markets and make investing decisions.

We offer the best parts of a startup environment — small team, high ownership, fast execution, and room to experiment — with the backing and stability of VERSANT, an independent publicly traded media company.

As an AI engineer, you will work on both an existing AI product with real user impact and greenfield projects with significant room for exploration. The work spans cutting-edge LLMs, large-scale data systems, financial reasoning, and research tooling, with opportunities to apply ideas from functional programming and graph-based systems where they create real advantage.

You will be joining a team of exceptional engineers, analysts, and investors working at the intersection of AI and public markets. A particularly rare part of this role is the level of direct access to experienced market professionals, including former hedge fund managers and top-tier analysts, whose insights can directly inform how you think about modeling, signals, and product design.

The Role

We're looking for a highly capable Senior AI Engineer to join our team to build the next generation of AI-powered equity research.

This role is for engineers who enjoy turning LLM and agentic AI capabilities into reliable product systems embedded in real-world workflows. It is especially well suited to people who want to work hands-on across architecture, implementation, and operations while helping define how AI capabilities get integrated into products used by individual investors.

You will design, build, and operate core components of our AI platform: distributed agentic workflows, retrieval and reranking systems, model integrations, and the infrastructure required to make these systems reliable, observable, and scalable in production.

This role sits within a small and growing, high-caliber team where individuals are expected to operate with a high degree of ownership and autonomy, contributing directly to core product, engineering, and AI systems decisions while working closely with peers, product stakeholders, and senior leadership in a highly collaborative, low-bureaucracy environment with direct access to decision-makers.

A genuine interest in investing, public markets, and fundamental business analysis is expected.

Your profile

What We're Looking For

• Bachelor's degree in Computer Science or equivalent practical experience

• 5+ years of experience designing, building, and maintaining software systems

• Strong backend expertise in at least one strongly typed language, preferably TypeScript

• Solid understanding of cloud computing primitives, especially AWS

• Strong understanding of agentic AI concepts such as tool use, function calling, state machines or graphs, retrieval and reranking, structured outputs, memory, guardrails, and evaluation

• Experience developing and deploying agentic workflows using frameworks such as LangChain, Mastra, or LangGraph

• Experience contributing to system design and technical decision-making

What You'll Do

• Build end-to-end distributed agentic AI solutions that are reliable and scalable

• Own complex features or subsystems from design through deployment and operation

• Collaborate cross-functionally to integrate AI capabilities into products and data pipelines

• Contribute to architectural decisions and technical standards for AI systems

• Maintain observability and operational health, including cost metrics, quality monitoring, drift detection, alignment, alerting, and incident response

• Support the team's overall technical growth

• Identify and mitigate risks in AI systems, including performance regressions, bias, and operational issues

• Use and improve model lifecycle management, monitoring, and evaluation frameworks

Desirable Skills & Experience

• Experience shipping and operating multiple GenAI or LLM-powered systems in production

• Hands-on experience debugging scaled LLM systems and participating in incident response

• Experience building RAG pipelines using embeddings and vector databases

• Familiarity with fine-tuning or adapting models for specific tasks

• Experience implementing evaluation pipelines, including human-in-the-loop workflows

• Experience building or maintaining evaluation suites for agentic systems in production

Location

Hybrid — 4 days on-site in Prague, Czech Republic / 1 day remote.