Senior Lead AI Engineer

At DraftKings, AI is becoming an integral part of both our present and future, powering how work gets done today, guiding smarter decisions, and sparking bold ideas. It's transforming how we enhance customer experiences, streamline operations, and unlock new possibilities. Our teams are energized by innovation and readily embrace emerging technology. We're not waiting for the future to arrive. We're shaping it, one bold step at a time. To those who see AI as a driver of progress, come build the future together.

As a Senior Lead Software Engineer on our AI Platform Team, you'll help lay the technical foundation that enables product teams across the company to build with GenAI quickly, safely, and at scale. 

This is a hands-on engineering opportunity to architect AI developer infrastructure - from orchestration runtimes to observability tooling - while serving as a Dev Champion who ensures our platform is powerful, safe, and accessible for engineers across the company.

• Build core AI infrastructure and tooling that powers internal development of GenAI agents, copilots, and assistive experiences — including runtimes, model gateways, orchestration layers, and SDKs.

• Enable product engineers to ship with AI by designing low-friction, reusable platform components that abstract away the complexity of agent orchestration (e.g., using LangGraph), vector search (e.g., via Weaviate or PGVector), prompt management, and model routing (e.g., through LiteLLM), evaluation framework like Ragas and monitoring using tools like Datadog or Langsmith

• Collaborate across product and infra teams to identify engineering pain points and deliver GenAI capabilities that boost productivity, reduce toil, and improve software quality.

• Operationalize AI in production, ensuring observability, performance, and safety. Build systems for model monitoring, prompt tracing, agent performance, and fallback logic — making AI feel reliable, not experimental.

• Own the full lifecycle of AI-powered features, from prototyping and proof-of-concepts to scalable platform integration.

• Stay close to the ecosystem — from LLM orchestration frameworks to agent lifecycle tooling and low-code builders — and help bring relevant innovations into our stack.

• Mentor teammates and influence platform direction, helping shape our standards for building safe, performant, and maintainable AI services.

• Strong software engineering background, with 7+ years of experience building backend systems, platforms, or internal tools that operate at scale.

• Experience working on developer enablement, infrastructure, or platform teams — especially those focused on CI/CD, productivity tooling, or automation.

• Proven ability to build and support AI-powered applications in production, such as retrieval-augmented generation (RAG) systems, task-driven agents, or LLM-integrated developer tools.

• Hands-on experience with the core components of modern AI platforms — including LLM orchestration frameworks, multi-agent execution environments, vector databases for retrieval workflows, and tools for prompt/agent observability and evaluation.

• Proficiency in Python and/or TypeScript/JavaScript.

• Experience or interest in low-code/no-code approaches to agent development or in building abstractions that enable non-specialists to integrate AI safely.

• Strong product mindset — you think about developer experience and maintainability, not just implementation.

• Excellent collaboration and communication skills; you enjoy working across teams and helping others level up.
   

#LI-OK1

We're a publicly traded (NASDAQ: DKNG) technology company headquartered in Boston. As a regulated gaming company, you may be required to obtain a gaming license issued by the appropriate state agency as a condition of employment. Don't worry, we'll guide you through the process if this is relevant to your role.