Senior Applied AI Engineer

About deepsense.ai deepsense.ai is a 120-person AI/ML consultancy with Anthropic and OpenAI partner credentials. For over a decade we've delivered applied AI projects for companies like J&J, Sky, John Deere, and GLS — spanning LLM applications, agents, MLOps, and data science. We're a people-first organization that believes in deep technical craft and real ownership. Our engineers don't just advise; they build things that run in production. About the role The Applied AI Engineer works close to the client across the whole engagement: in the presales conversations understanding what they actually need, drafting the architecture for it, and then delivering it hands-on, super close with the client. You'll move across that work fluidly — one moment shaping the approach in a scoping workshop, the next committing code to their repo and owning a production agent in their environment. You'll work alongside our own team and the client's, and you'll be equally at home in a discovery workshop and a pull request review. Daily tasks: - Partner with Delivery Managers to scope and win AI engagements — run technical discovery, design solution architectures, build and demo POCs that help win the work. - Act as the primary technical advisor during early post-sales phases, shaping how clients build on top of LLMs and agentic systems. - Work hands-on inside client engagements — in their systems and close to their team — shipping production code and, where the engagement calls for it, owning critical AI deployments end to end. - Design and build LLM-powered applications: RAG pipelines, multi-agent systems, MCP integrations, evaluation frameworks, and production inference stacks. - Run technical workshops and architecture reviews; transfer knowledge in ways that build lasting capability in client teams. - Contribute to reusable internal assets: solution blueprints, reference implementations, prompt libraries, evaluation toolkits. - Stay at the leading edge of the applied AI space — new models, tooling, and patterns — and bring that knowledge into client work. You must have: 4+ years of software engineering experience, with at least 2 years working on AI/ML or LLM-powered systems in production. Hands-on production experience with LLMs: prompting, context engineering, agent architectures, tool use, RAG, evaluation. Strong Python skills and experience shipping software that real users depend on. Demonstrated ability to work directly with clients — you can run a technical scoping call, facilitate a workshop, and earn trust quickly with engineers and non-engineers alike. Experience owning deliverables end-to-end in ambiguous environments without close supervision. Familiarity with cloud platforms (GCP / AWS / Azure) and containerized deployment (Docker, Kubernetes). You may have: Experience supporting the sales process as the technical expert — building POCs, scoping, and answering clients' technical questions before a deal is signed. Hands-on experience with agentic frameworks: LangGraph, CrewAI, Pydantic AI, or MCP server development. Familiarity with LLMOps tooling: 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. Must have: Python, LLMs, RAG, Cloud, Docker, Kubernetes, AI, Cloud platform Nice to have: LangGraph, CrewAI, MCP server , LangSmith, Langfuse