Overview
Hands-on engineering role focused on designing and building generative AI solutions
Owns technical implementation of AI initiatives - from prototype → production deployment
Works closely with AI Product Delivery Leads, business stakeholders, and engineering teams
Deep, day-to-day development using LLMs, APIs, and AI frameworks
Duties
- Design and implement generative AI solutions (RAG, automation, agentic workflows)
- Translate product requirements and use cases into scalable technical architectures
- Build and optimize prompt strategies, LLM workflows, and agent-based systems
- Develop Retrieval-Augmented Generation (RAG) pipelines using enterprise data
- Integrate LLMs into applications via APIs and microservices
- Collaborate with product and delivery leads to iterate on features and solutions
- Evaluate and improve model performance (accuracy, latency, cost, reliability)
- Implement logging, monitoring, and guardrails for AI systems
- Rapidly prototype and test new AI capabilities
- Leverage AI tools to accelerate development, debugging, and experimentation
Requirements
- 3-6+ years of software engineering experience
- Strong programming skills (Python preferred)
- Hands-on experience working with LLMs (e.g., OpenAI, Claude, open-source models)
- Experience building APIs and working with backend systems
- Familiarity with data pipelines, system integration, and cloud environments
- Understanding of how AI/ML systems work (not just usage, but implementation)
Strong Plus
- Experience with RAG architectures and vector databases
- Familiarity with frameworks (LangChain, LlamaIndex, etc.)
- Experience with agentic workflows or tool-using LLM systems
- Exposure to fine-tuning or deploying open-source models
- Experience in enterprise-scale environments