Applied AI Engineer (Automation)

Summary

Fusemachines is a leading AI strategy, talent, and education services provider. As an Applied AI Engineer (Automation), you will deliver high-impact AI and automation solutions for clients, owning work from requirements discovery through prototype and production deployment.

Responsibilities

• Design & Deploy: Design, develop, and deploy tailored AI and automation solutions aligned to client objectives
• Build Workflows & Services: Translate business problems into production-grade AI workflows and services using Python, automation tools (n8n/Make/Zapier or similar), and LLM platforms/APIs (e.g., OpenAI, IBM watsonx.ai, Amazon Bedrock), plus retrieval systems
• Agentic Systems: Build and deploy agentic workflows using LangChain, LangGraph, and Google ADK, including tool calling and structured outputs
• Retrieval & Knowledge Systems: Implement RAG pipelines using vector databases and search technologies (e.g., Pinecone, Elasticsearch, pgvector) and graph databases when appropriate
• Prototype → Production: Ship fast prototypes, then harden them into scalable systems (testing, reliability, deployment, monitoring) independently or with a team
• Client Partnership: Participate in discovery, run technical calls/demos when needed, and communicate tradeoffs clearly to client and internal stakeholders
• Ongoing Support & Iteration: Improve deployed solutions through feature work, bug fixes, monitoring, prompt/model improvements, and additional automations
• Documentation: Produce clear technical documentation, client demos, and internal playbooks to enable reuse and scalability
• Continuous Learning: Stay current on LLM tooling and delivery best practices to improve quality and speed

Skills

• 3–8 years of software or AI engineering experience (mid-to-senior)
• 2–3+ years of AI Automation, Generative AI, or Agentic AI (mid-to-senior)
• Strong Python engineering skills and experience building APIs/services (e.g., FastAPI)
• Hands-on experience integrating LLMs (e.g., OpenAI APIs or equivalents), including prompt design, structured outputs, and basic evaluation practices
• Experience with at least one workflow automation platform (n8n, Make, Zapier, or similar) and building reliable integrations
• Familiarity with RAG fundamentals and retrieval systems (embeddings, vector search); exposure to vector databases and/or Elasticsearch
• Production engineering fundamentals: Docker, cloud deployment (AWS/GCP/Azure/IBM), and experience with async/queuing patterns (e.g., Celery, Redis, Kafka)
• Comfort operating in a client-facing environment: technical calls, demos, and collaborating with cross-functional stakeholders
• Experience with fine-tuning LLMs or other ML models; broader ML exposure is a plus (not required)
• Familiarity with observability and tracing (e.g., LangSmith, OpenTelemetry) and prompt/version lifecycle management
• Experience with graph databases / knowledge graphs
• Familiarity with data governance and AI governance concepts (PII handling, auditability, access controls, risk awareness)
• Prior consulting experience or work in fast-paced startup environments

Qualifications

Must Haves

• 3–8 years of software or AI engineering experience (mid-to-senior)
• 2–3+ years of AI Automation, Generative AI, or Agentic AI (mid-to-senior)
• Strong Python engineering skills and experience building APIs/services (e.g., FastAPI)
• Hands-on experience integrating LLMs (e.g., OpenAI APIs or equivalents), including prompt design, structured outputs, and basic evaluation practices
• Experience with at least one workflow automation platform (n8n, Make, Zapier, or similar) and building reliable integrations
• Familiarity with RAG fundamentals and retrieval systems (embeddings, vector search); exposure to vector databases and/or Elasticsearch
• Production engineering fundamentals: Docker, cloud deployment (AWS/GCP/Azure/IBM), and experience with async/queuing patterns (e.g., Celery, Redis, Kafka)
• Comfort operating in a client-facing environment: technical calls, demos, and collaborating with cross-functional stakeholders

Nice to Haves

• Experience with fine-tuning LLMs or other ML models; broader ML exposure is a plus (not required)
• Familiarity with observability and tracing (e.g., LangSmith, OpenTelemetry) and prompt/version lifecycle management
• Experience with graph databases / knowledge graphs
• Familiarity with data governance and AI governance concepts (PII handling, auditability, access controls, risk awareness)
• Prior consulting experience or work in fast-paced startup environments