AI Engineer

As an AI Engineer, you will design and build next-generation AI applications that leverage agentic workflows, large language models, and enterprise knowledge systems. You will work across the full software lifecycle, from architecture and backend development to deployment, evaluation, monitoring, and optimization.

The ideal candidate is excited about the potential of AI while maintaining strong engineering judgment, carefully balancing reliability, security, performance, operational complexity, cost, and business value.

Core Technical Areas

Agent Architectures Multi-Agent Systems

• Agent orchestration frameworks such as Google ADK, LangChain, LangGraph, DeepAgents, AutoGen, CrewAI, or similar
• Planning and reasoning workflows
• Tool integration and function calling
• State and memory management
• Human-in-the-loop review processes
• Error handling and recovery mechanisms

LLMs Generative AI

• Transformer fundamentals and attention mechanisms
• Prompt engineering and structured outputs
• Context management and token optimization
• Fine-tuning and model customization
• Working with both commercial and open-source models

RAG Knowledge Systems

• Semantic and hybrid search
• Document ingestion and processing pipelines
• Embeddings and retrieval strategies
• Reranking techniques
• Vector databases such as Pinecone, Qdrant, Weaviate, pgvector, or Vertex AI Vector Search
• Knowledge access controls and source citation capabilities

Backend Cloud Engineering

• Python, FastAPI, and asynchronous programming
• REST and streaming APIs
• Event-driven and microservice architectures
• Docker and cloud deployment
• Security, monitoring, and observability

AI-Augmented Development

• Development acceleration using tools such as Cursor, GitHub Copilot, Claude Code, or similar
• Frontend development using React, Next.js, and TypeScript

Evaluation Reliability

• Agent evaluation and testing

• Observability and tracing

• Prompt security and guardrails

• Latency, quality, and cost monitoring

• Tools such as LangSmith, Phoenix, OpenTelemetry, and cloud-native monitoring platforms

• • Design, build, and maintain agentic and multi-agent AI systems for complex business workflows
  • Develop scalable backend services and APIs that support AI-powered applications
  • Build and maintain RAG pipelines, retrieval systems, and enterprise knowledge platforms
  • Implement evaluation frameworks to measure quality, reliability, safety, latency, and cost
  • Establish monitoring, tracing, security, and governance practices for production AI services
  • Collaborate with product, engineering, and business stakeholders to deliver impactful AI solutions
  • Evaluate emerging AI models, frameworks, and tools to improve product quality and development efficiency
  • Contribute to architecture decisions and engineering best practices

Required Qualifications

• 4+ years of software engineering and/or AI engineering experience
• Proven experience delivering production-grade software and AI applications
• Hands-on experience building agentic applications involving multi-step workflows, tool usage, orchestration, memory, and fault handling
• Strong proficiency in Python and FastAPI
• Experience with asynchronous programming, API development, and containerized applications
• Experience with LLM-based applications, RAG architectures, vector databases, and model evaluation
• Familiarity with agent frameworks such as Google ADK, LangChain, LangGraph, DeepAgents, AutoGen, CrewAI, or similar
• Experience deploying secure, scalable applications in cloud environments
• Strong problem-solving, communication, and collaboration skills

Preferred Qualifications

• Experience with Google Cloud Platform, Vertex AI, Gemini, and Google's agent ecosystem
• Experience with observability platforms such as LangSmith, Phoenix, or OpenTelemetry
• Experience building full-stack AI applications using React, Next.js, and TypeScript
• Knowledge of CI/CD, infrastructure automation, and modern DevOps practices
• Experience working in enterprise-scale AI environments

#LI-MF2