Staff Engineer / Full-Stack Engineer – Generative AI

We are a Digital Product Engineering company that is scaling in a big way! We build products, services, and experiences that inspire, excite, and delight. We work at scale — across all devices and digital mediums, and our people exist everywhere in the world (18000+ experts across 38 countries, to be exact). Our work culture is dynamic and non-hierarchical. We're looking for great new colleagues. That's where you come in!

We are seeking a highly skilled Full-Stack Engineer with expertise in Python, React, and Generative AI fundamentals to develop and deploy LLM-powered applications. The ideal candidate will be adept at finding, testing, and prototyping GenAI-based solutions, transforming them into functional and user-friendly web-based chat applications while ensuring seamless deployment into enterprise platforms.

Key Responsibilities:

Web-Based Chatbot Development (40%)

• Design, develop, and deploy a web-based chatbot application, working across:
  • Front-end (20%) – Developing an intuitive and responsive UI using React.
  • Back-end (60%) – Implementing robust server-side logic using Python.
  • DevOps (20%) – Managing deployments, CI/CD pipelines, and infrastructure.

LLM-Based Experimentation & Prototyping (40%)

• Test and utilize modern LLM-based concepts such as chains, agents, entity memory, and prompt engineering.
• Develop multi-prompt workflows using frameworks like LangChain.
• Build LLM-powered agents with stateful interactions.

Integration & Strategic Development (20%)

• Integrate chatbot solutions into existing Woven software and platforms.
• Advise on Generative AI strategy for Woven and beyond.

Required Qualifications:

• 4+ years of experience as a Full-Stack Developer using Python and JavaScript/TypeScript.
• Expertise in Generative AI fundamentals, with hands-on experience in LLM-powered applications.
• Strong experience deploying applications in production environments, including:
  • Setting up and maintaining CI/CD pipelines.
  • Infrastructure-as-code, AWS resources, and Kubernetes.
• Experience with prompt engineering techniques (both known and experimental).
• Knowledge of machine learning, especially in NLP and Transformer models.
• Experience integrating with OpenAI API or GCP Vertex AI.
• Proven ability to build stateful web applications using:
  • React, FastAPI, DynamoDB, PostgreSQL, WebSockets, Server-Side Events.

Good to Have:

• Proficiency in TypeScript.
• Knowledge of PostgreSQL and database optimization techniques.

What We Offer:

• Competitive salary and benefits package.
• Opportunity to work on cutting-edge GenAI applications.
• Career development in a fast-evolving AI landscape.
• Collaborative multicultural environment with innovation-driven teams.