The Role
Lead end-to-end development and integration of AI features (LLMs/ML) into web/mobile apps and APIs. Design AI-first UX, craft and optimize system prompts, build agentic workflows (LangChain/CrewAI/AutoGen), implement error-handling and hybrid cloud/on-prem deployments, and collaborate within product squads using Agile/Scrum.
Summary Generated by Built In
We are currently looking for a dedicated Senior AI Product Engineer to join one of our clients' teams. If you're looking for an exciting opportunity to grow in an innovative environment, this could be the perfect fit for you.
Key Responsibilities
- AI Feature Delivery & Integration
- Lead the end-to-end development of AI-powered features, from initial prototyping to production deployment.
- Integrate LLMs and ML models into existing web/mobile applications and backend APIs.
- Design "AI-first" user journeys, ensuring features like autocomplete, summarization, and intelligent search are intuitive and high-performing.
2. Prompt Engineering & Agentic Workflows
- Craft, test, and optimize complex system prompts to ensure high-quality, safe, and consistent model outputs.
- Build and manage Agentic workflows (using frameworks like LangChain, CrewAI, or AutoGen) to automate multi-step business processes.
- Implement robust error-handling and "fallback" logic for non-deterministic AI responses to maintain a seamless UX.
3. Squad Collaboration (The "Product" Side)
- Act as the AI subject matter expert within your Product Squad, helping PMs understand what is technically feasible vs. what is "AI hype."
- Work closely with UX/UI designers to handle AI-specific design challenges (e.g., streaming text latency, "thinking" states, and user feedback loops).
- Participate in agile ceremonies, contributing to grooming, planning, and rapid iteration.
4. Hybrid Implementation
- Develop applications that can switch seamlessly between Cloud APIs (for speed/innovation) and On-Premises models (for data privacy and cost-efficiency).
- Ensure that AI features are performant across different hosting environments without sacrificing user experience.
Job requirements
- 8+ years in Full-Stack or Backend Software Engineering.
- 3+ years of experience specifically building and shipping AI-integrated features.
- Proven ability to work in an Agile/Scrum environment within a "Squad" structure.
- Mastery of Python and/or TypeScript/JavaScript (React/Node.js).
- Hands-on experience with LangChain, LlamaIndex, or Haystack.
- Expertise in RESTful APIs, GraphQL, and working with Vector DBs (Pinecone, Weaviate).
- Familiarity with Docker, Kubernetes, and deploying to AWS/Azure or local GPU environments.
Skills Required
- 8+ years in Full-Stack or Backend Software Engineering
- 3+ years building and shipping AI-integrated features
- Proven ability to work in an Agile/Scrum environment within a Squad structure
- Mastery of Python and/or TypeScript/JavaScript (React/Node.js)
- Hands-on experience with LangChain, LlamaIndex, or Haystack
- Expertise in RESTful APIs, GraphQL, and working with Vector DBs (Pinecone, Weaviate)
- Familiarity with Docker, Kubernetes, and deploying to AWS/Azure or local GPU environments
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company







