Job description
This role will start off as a temporary contract hourly position. We anticipate the duration lasting approximately 12 weeks, but may extend.
Detroit Labs was founded in 2011 with a vision for building digital products, services, and the teams that power them. We create digital solutions that transform the way our clients do business. We build genuine relationships based on respect, trust, and results. We foster a diverse and inclusive culture that values people - providing them with the tools, resources, and support they need to thrive professionally, exceed client expectations, and be themselves at work. We have a variety of client teams we work with ranging from startups to Fortune 500 companies so there are always new and exciting projects going on.
Detroit Labs is looking for an experienced Senior AI/ML Engineer to join an exciting project with an existing client focused on turns reactive risk management into real-time strategic foresight using predictive AI, expert validation, and decision-ready intelligence. This role will Serve as the AI Lead to drive build, test, document, deploy, and continuously innovate for AI solutions. It will focus on the architecture, development, and deployment of intelligent agent systems powered by large language models. With full stack experience you’ll leverage Python (FastAPI), TypeScript (React/Next.js), and cloud platforms (AWS, GCP) to bring advanced AI capabilities to life.
- 10+ years of experience in full stack software engineering, preferably with production SaaS platforms
- Advanced proficiency in Python (FastAPI); frontend development in TypeScript/React/Next.js; deep experience with Azure Cloud
- Extensive hands-on experience with LLMs and generative AI—building, deploying, and optimizing applications through APIs and open-source frameworks (OpenAI, Hugging Face, LangChain, LangGraph)
- Expertise in MCP concepts including prompt structures, shared model state, and protocol-driven agent interactions
- Deep fluency in prompt engineering, agent tool integration, chaining, and decomposition of LLM tasks for scalable use
- Experience with multi-agent orchestration and deployment on scalable infrastructure
- Knowledge of CI/CD for rapid SaaS releases; commitment to code quality, maintainability, and documentation
- Strong communication skills for technical and non-technical audiences
Responsibilities
Architect, implement, and maintain full stack AI applications using modern backend (Python, FastAPI), frontend (TypeScript, Next.js or React), and cloud platforms (GCP, AWS)
Develop and deploy LLM-powered agent systems including planning, memory, tool usage, and user interaction flows
Design, develop, and integrate Model Context Protocol (MCP)-compliant servers for structured, context-rich interactions between LLM agents and models
Build and maintain APIs, agent orchestration frameworks (e.g., AutoGen, CrewAI, LangGraph), and robust multi-agent coordination pipelines
Lead all aspects of prompt engineering: generation, optimization, chaining, context/rag, and dynamic deconstruction for LLM workflows
Integrate and manage vector and semantic databases (e.g., Qdrant) for persistent agent memory, context retrieval, and semantic search
Collaborate with cross-functional teams to launch intelligent user-facing tools and ensure fast, reliable, and scalable SaaS delivery
Drive best practices for observability, debugging, and LLM evaluation, including test harnesses and human-in-the-loop review
Understanding of data privacy, AI ethics, and model governance for enterprise deployments.
Mentor junior engineers, champion full stack and AI/ML culture, and stay abreast of AI research and SaaS platform trends
Compensation for this role is on an hourly basis and is $120/hr.
Equipment to complete your work
Remote friendly position
