Remote job
AI Engineer
Job details
About this role
Role overview
An AI engineering role focused on designing, evaluating, and operating intelligent systems built on foundation models at production scale. The position bridges cutting-edge research and production-grade software engineering, covering multi-agent architectures, retrieval pipelines, and safe deployment of autonomous workflows across industries.
Responsibilities
- Architect multi-agent systems with autonomous planning, tool selection, and self-reflection using frameworks such as LangGraph, AutoGen, or CrewAI. - Build and tune Retrieval-Augmented Generation pipelines with vector databases like Pinecone, Weaviate, or Milvus and advanced hybrid search techniques. - Connect AI agents to internal tools, secure data sources, and third-party APIs through the Model Context Protocol. - Evaluate foundation and fine-tuned open-source models for balanced cost, latency, and accuracy outcomes. - Deploy and operate AI workloads in cloud-native environments with automated monitoring for model drift, hallucination rates, and token cost. - Design Human-in-the-Loop interfaces with product and frontend partners so users can safely steer and review AI outputs. - Implement deterministic guardrails and safety controls addressing bias, privacy, and global AI regulatory compliance.
Requirements
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, or a related technical field. - Mastery of Python and TypeScript, with Go or Rust considered a plus for high-performance inference services. - Deep experience with orchestration libraries such as LangChain, LlamaIndex, and specialized agentic frameworks. - Strong understanding of embedding models, chunking strategies, and large-scale unstructured data management. - Proficiency with Docker, Kubernetes, and CI/CD pipelines adapted to machine learning lifecycles (MLOps/LLMOps). - Expertise in building secure, type-safe APIs using REST, GraphQL, or tRPC as the interface for AI features. - Ability to translate opaque AI behaviors into clear technical and business insights for stakeholders.
Nice to have
- Expert proficiency with AI-native IDEs like Cursor or GitHub Copilot to accelerate the SDLC. - OpenTelemetry experience for tracing complex, multi-step reasoning chains. - Specialized knowledge of token optimization, caching strategies, and inference cost management at scale. - Cloud AI certifications such as AWS Certified AI Practitioner or Azure AI Engineer Associate.