Artificial Intelligence Engineer

Overview

We seek an experienced Artificial Intelligence Engineer to create innovative AI-driven products and business workflows. This position emphasizes utilizing state-of-the-art generative AI technologies—not foundation model training—to address real-world business challenges effectively. The role involves designing, developing, and deploying AI applications that leverage large language models, retrieval systems, agent workflows, multimodal models, and cutting-edge AI frameworks.

Responsibilities

• Design, build, and deploy production-quality AI solutions based on modern large language and multimodal models.
• Implement Retrieval-Augmented Generation systems with embeddings, vector databases, hybrid search techniques, and knowledge retrieval mechanisms.
• Create intelligent autonomous agents with tool usage, function invocation, orchestration, and task automation capabilities.
• Integrate commercial and open-source foundational AI models including but not limited to OpenAI, Anthropic, and Google Gemini.
• Assess and enhance AI models, development frameworks, and prompting methods to boost performance, reliability, latency, and cost-efficiency.
• Develop APIs and backend systems that provide AI functionalities to internal and external applications.
• Construct automated pipelines to evaluate AI prompts, agents, and workflows, ensuring high-quality outputs.
• Establish monitoring, observability, feedback, and safety guardrails for AI systems in live environments.
• Collaborate with project managers, UX designers, software developers, and stakeholders to rapidly prototype and evolve solutions.
• Identify business opportunities where AI can optimize processes and enhance employee experiences.
• Contribute to AI solution architecture, coding standards, and best engineering practices within the organization.
• Remain up to date with trends and innovations in AI technologies and promote continuous technical advancements.

Required Skills & Experience

• 3 to 5 years of professional experience in software development.
• 1 to 3 years experience developing production-grade applications using large language models or generative AI frameworks.
• Proficient in Python programming language.
• Hands-on experience with AI development frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, or DSPy.
• Knowledge and implementation experience of Retrieval-Augmented Generation architectures and vector databases like Pinecone, Weaviate, Milvus, Chroma, or pgvector.
• Familiarity with integrating LLM APIs from providers such as OpenAI, Anthropic, or Google Gemini.
• Strong grasp of prompt engineering techniques, structured response formatting, tool and function invocation.
• Experience designing RESTful APIs and embedding AI services into existing software systems.
• Comfortable with cloud environments including AWS, Google Cloud, or Microsoft Azure.
• Experience with containerization (Docker), version control (Git), CI/CD pipelines, automated testing, and contemporary software engineering practices.
• Excellent communication skills able to explain complex technical concepts to both technical and non-technical team members.

Preferred Qualifications

• Experience creating autonomous or multi-agent AI systems.
• Familiarity with AI evaluation and monitoring platforms such as LangSmith, Arize Phoenix, Weights & Biases, Promptfoo, or DeepEval.
• Knowledge of AI interoperability standards including Model Context Protocol (MCP) or Agent-to-Agent communication (A2A).
• Experience working with multimodal AI including vision, audio, speech, or document comprehension.
• Capable of deploying open-source models using tools like vLLM, Ollama, Hugging Face, or similar inference engines.
• Experience with Kubernetes and scalable cloud infrastructure management.
• Background in MLOps, feature engineering, or conventional machine learning practices.
• Experience developing internal AI products, developer platforms, or workflow automation solutions.

Success Metrics

• Delivered and deployed AI solutions used organization-wide within the first year.
• Enhanced existing AI offerings through testing and optimization.
• Developed reusable architectural patterns for agents, RAG systems, and prompt engineering.
• Assisted with setting engineering guidelines for AI app development.
• Built strong technical partnerships with engineering teams and business stakeholders.

Technology Stack

• Python
• Large Language Models from OpenAI, Anthropic, Google Gemini
• Frameworks: LangGraph, LangChain, LlamaIndex
• Vector databases: Pinecone, pgvector, Weaviate
• FastAPI
• Docker, Kubernetes
• GitHub Actions
• PostgreSQL
• Cloud Platforms: Google Cloud Platform, AWS