Applied AI Engineer (all genders)

In this role you design, build, and deploy production-grade agentic AI systems for enterprise clients. You work closely with client teams to drive architecture, design sessions, and reusable accelerators that scale beyond a single engagement. You operate across the full tech stack, balancing performance, cost, and safety while delivering real-world AI capabilities. You join a culture that values impact at speed and breadth across industries.

• diversity and inclusion
• learning and development opportunities
• dedicated mentoring and onboarding
• flexible work locations
• supportive culture and career growth

• Design and build end-to-end agentic systems: multi-agent orchestration, RAG pipelines, policy routing, tool invocation, memory management, observability
• Own RAG pipelines: embeddings, chunking, vector search, and context window tuning against quality targets
• Integrate multiple LLM providers (OpenAI, Anthropic, Vertex AI, open-source) with fallback routing, token, cost, and latency mgmt
• Implement LLMOps in production: eval harnesses, prompt versioning, observability tooling, cost and safety monitoring
• Collaborate with client engineering teams on workshops, PoCs, code-with sessions, and architecture walkthroughs
• Create reusable patterns, accelerators, and playbooks that scale beyond a single engagement
• Define and use metrics for agent accuracy, latency, safety, and cost-effectiveness; present findings to stakeholders in business terms

• Extensive years of software engineering experience in production environments
• Hands-on experience designing and deploying production-grade agentic AI solutions
• Proven experience with agentic orchestration frameworks: LangGraph, CrewAI, AutoGen, or equivalent (production depth)
• Direct production experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) with provider abstraction, token management, latency and cost tradeoffs
• RAG pipeline ownership: embeddings, chunking, vector databases, context engineering
• LLMOps fundamentals: eval harness design, prompt versioning, production observability
• Cloud-native engineering maturity: Kubernetes, Docker, microservices, serverless, CI/CD, IaC (Terraform or Helm)
• Strong Python; Java or equivalent back-end language
• Production debugging and observability experience
• Quality of experience valued; production shipping of multiple agentic systems preferred over generalist AI exposure

• Client-facing collaboration
• Workshops and architecture walkthroughs with clients
• Clear technical and business communication
• agentic orchestration frameworks (LangGraph, CrewAI, AutoGen)
• LLM APIs (OpenAI, Anthropic, Vertex AI) in production
• RAG pipelines (embeddings, chunking, vector databases)