Applied AI Engineer

About the role

Appsilon is seeking an Applied AI Engineer to design, build, and deploy AI agents and generative AI solutions for enterprise clients. You will work on production‑grade pipelines that combine large language models, retrieval systems, and external tools to solve real‑world problems.

Key responsibilities

• Develop AI agents with domain‑specific context, enabling multi‑step reasoning, tool use, and autonomous decision‑making.
• Design and implement agentic workflows that orchestrate LLMs, retrieval‑augmented generation, and external APIs.
• Integrate agents into client applications, APIs, and enterprise systems.
• Evaluate, debug, and optimize agent performance using structured testing, tracing, and observability tools.
• Deploy and maintain generative AI services as APIs, micro‑services, or cloud‑native components.
• Document implementations and contribute to LLMOps best practices.

Required profile

• Proven experience delivering AI agents or agentic systems in production environments.
• Deep knowledge of LLM orchestration frameworks and prompt engineering techniques.
• Strong Python programming skills and ability to build robust backend services.
• Excellent communication and collaborative mindset.

Required skills

• Python
• LangChain, LangGraph, CrewAI, Autogen, Claude Agent SDK
• OpenAI, Anthropic, Google LLM APIs
• AWS, Azure, GCP
• Docker, Kubernetes
• Pinecone, Weaviate, Qdrant, pgvector
• LangSmith, Langfuse, Weights & Biases
• scikit‑learn, PyTorch, TensorFlow

What we offer

• 100% remote work with flexible schedule.
• Competitive B2B compensation with transparent ranges.
• Opportunity to work on impactful AI products for Fortune 500 and scientific industries.