Senior AI Engineer

We are looking for a hands-on Senior/Staff AI Engineer to build and scale production-grade AI systems used by enterprise customers.
You will design, develop, and operate AI-native product capabilities, including LLM-powered workflows, AI agents, evaluation frameworks, and the infrastructure required to run them reliably in production.
This role is ideal for an engineer who has already shipped AI products to real users and understands the challenges of reliability, observability, scalability, security, and enterprise adoption.
Required Qualifications5+ years of software engineering experience.Proven experience shipping LLM-based applications to production.Experience building AI Agents, autonomous workflows, or multi-step AI systems.Strong proficiency in Python, react and Node.jsExperience with OpenAI, Anthropic, Gemini, or open-source LLMs.Strong understanding of:Prompt EngineeringRAG ArchitecturesEmbeddings & Vector SearchLLM Evaluations (Evals)Structured OutputsFunction/Tool CallingExperience with vector databases such as Pinecone, Weaviate, Qdrant, pgvector, or Milvus.Experience designing microservices, APIs, and distributed systems.Strong knowledge of AWS, Azure, or GCP.Experience with Docker, Kubernetes, CI/CD, and observability tooling.Experience implementing reliability patterns such as:IdempotencyRetriesFault ToleranceRate LimitingCircuit BreakersStrong understanding of security, scalability, and production operations.
Preferred QualificationsExperience with Temporal, LangGraph, CrewAI, AutoGen, or similar orchestration frameworks.Experience migrating between OpenAI, Anthropic, Gemini, or other model providers.Experience building AI products in regulated environments (Healthcare, Finance, HR).Experience with AI observability platforms such as LangSmith, LangFuse, Arize, or Helicone.Experience with Kafka and event-driven architectures.Open-source contributions within AI, ML, or developer tooling.
Responsibilities:Design and develop AI-powered product features using modern LLMs and agentic architectures.Build and operate production-grade AI systems, including:AI AgentsRAG pipelinesTool-calling workflowsModel routing and orchestrationAutomated evaluation frameworksDesign scalable backend services, APIs, and distributed systems.Build observability and monitoring solutions for AI performance, reliability, latency, and cost.Optimize inference pipelines for scalability, quality, and operational efficiency.Drive technical decisions around model selection, architecture, and platform design.Collaborate directly with customers to understand requirements and translate feedback into product improvements.Deliver features end-to-end, from concept through production deployment.