B
Lead AI Engineer
HybridFull-timeAI EngineeringEnterprise Software
Build and operate a next-generation agentic AI platform, taking AI features from concept to production for enterprise customers. The role is hybrid and requires strong ownership of reliability, safety, cost, and customer outcomes.
Responsibilities
- Design, build, and evolve production agentic systems that can reason, plan, execute, and adapt.
- Take AI features from concept through production in a new-product environment.
- Write and review production code across AI pipelines, inference services, and orchestration layers.
- Develop agent frameworks that balance autonomy with determinism, observability, and safety.
- Integrate and operate commercial and open-source LLMs, including model selection, embeddings, RAG, and inference optimization.
- Address hallucinations, model drift, prompt regressions, and other production failure modes.
- Deploy and operate AI services on AWS, Azure, and GCP, including secure enterprise deployments.
- Build scalable inference and orchestration architectures using containers, APIs, and distributed systems.
- Make trade-offs across latency, cost, accuracy, scalability, and maintainability; keep the platform supportable and debuggable.
- Coordinate with stakeholders and global teams, and mentor junior team members.
Requirements
- At least 9 years of professional software development experience, including significant experience shipping B2B products to external customers.
- Expertise in Python or Java and production system design.
- A track record of building, deploying, and operating AI-powered products in production.
- Hands-on experience with LLMs and generative AI applications, such as agents, copilots, automation, or decision systems.
- Strong knowledge of agent frameworks and orchestration, prompt engineering, tool use, RAG, vector search, evaluation, monitoring, safety, and enterprise controls.
- Experience with tools such as LangGraph, LangChain, LlamaIndex, Google ADK, vector databases, and managed or versioned prompts.
- Experience with managed LLM platforms and direct APIs, such as AWS Bedrock, SageMaker, Vertex AI, OpenAI, or Anthropic.
- Experience with multi-agent systems or complex agent workflows and deploying LLMs at scale, including Kubernetes, model serving, or GPU optimization.
- Ability to build reusable components, SDKs, and APIs; work across teams; make decisions amid ambiguity; and mentor junior engineers.