Senior Applied AI Engineer

deepsense.ai is a 120-person AI/ML consultancy with Anthropic and OpenAI partner credentials. For over a decade they have delivered applied AI projects for companies like J&J, Sky, John Deere, and GLS — spanning LLM applications, agents, MLOps, and data science.

• 4+ years of software engineering experience, with at least 2 years on AI/ML or LLM-powered systems in production.
• Hands-on production experience with LLMs, including prompting, context engineering, agent architectures, tool use, RAG, and evaluation.
• Strong Python skills with experience shipping software relied upon by real users.
• Ability to work directly with clients, run technical scoping calls, facilitate workshops, and build trust.
• Experience owning deliverables end-to-end in ambiguous environments without close supervision.
• Familiarity with cloud platforms (GCP, AWS, Azure) and containerized deployment (Docker, Kubernetes).

Nice to have:

• Experience supporting the sales process as a technical expert by building POCs and answering technical questions.
• Hands-on experience with agentic frameworks such as LangGraph, CrewAI, Pydantic AI, or MCP server development.
• Familiarity with LLMOps tooling like LangSmith, Langfuse, W&B or equivalent.
• Experience building in regulated-industry environments (finance, healthcare, manufacturing).
• Exposure to model evaluation methodologies or LLM-as-a-judge patterns.

• Partner with Delivery Managers to scope and win AI engagements by running technical discovery, designing solution architectures, and building/demoing POCs.
• Act as the primary technical advisor during early post-sales phases.
• Work hands-on inside client engagements shipping production code and owning critical AI deployments end to end.
• Design and build LLM-powered applications including RAG pipelines, multi-agent systems, MCP integrations, evaluation frameworks, and production inference stacks.
• Run technical workshops and architecture reviews; transfer knowledge to client teams.
• Contribute to reusable internal assets like solution blueprints, reference implementations, prompt libraries, and evaluation toolkits.
• Stay updated on new models, tooling, and patterns in applied AI and integrate that knowledge into client work.