About this role
Designing, developing, and deploying AI-powered applications forms the core of daily operations at AIFT. The engineering group builds digital-first products that integrate Generative AI and Large Language Models into internal platforms and business workflows, transforming practical challenges into scalable production systems. This team collaborates across engineering, product, data, and business units to prototype new concepts, evaluate models, and implement monitoring mechanisms that optimize quality and latency.
Created to drive the development and adoption of artificial intelligence solutions across the organization, the function requires someone who navigates ambiguous problems independently. Ideal candidates combine solid software engineering fundamentals with hands-on experience in building LLM-driven applications, bridging the gap between high-level business goals and technical execution.
What you will do
- Design and launch production-ready applications powered by Generative AI and Large Language Models.
- Implement advanced techniques such as retrieval-augmented generation, prompt engineering, and autonomous agents.
- Connect language models to current enterprise infrastructure, backend services, and APIs.
- Establish evaluation frameworks and monitoring tools to track system reliability, latency, and cost.
- Partner with cross-functional stakeholders to translate operational needs into robust technical requirements.
- Prototype new concepts rapidly to validate feasibility before scaling them into stable architectures.
What you need
- Bring three or more years of professional background in software development, machine learning engineering, or a related discipline.
- Demonstrate strong programming abilities in Python alongside foundational software engineering practices.
- Possess practical exposure to deploying commercial or open-source large language models and associated frameworks.
- Understand retrieval-augmented generation, vector databases, embeddings, and modern application architecture.
- Build reliable backend services, APIs, and data pipelines to support production deployments.
- Familiarize with cloud computing environments including AWS, GCP, or Azure.
- Communicate effectively with technical and non-technical teams to drive project execution.
Nice to have
- Experience building AI agents or agentic workflows, including multi-step reasoning and tool integration.
- Experience with LLM evaluation, observability, guardrails, or AI application monitoring.
- Experience with vector databases or search technologies such as Elasticsearch, OpenSearch, Pinecone, Weaviate, or similar tools.
- Experience with MLOps / LLMOps, model deployment, CI/CD, Docker, or Kubernetes.
- Experience optimizing AI applications for latency, scalability, reliability, and cost.
Skills and tech stack
Questions candidates ask
What programming languages and tools will I use?
You will utilize Python alongside cloud platforms like AWS, GCP, or Azure. The stack also involves working with commercial or open-source LLMs, vector databases, and various backend integration tools.
Who will I work with on a regular basis?
You will work closely with Product, Engineering, Data, and business stakeholders. This collaboration helps identify high-impact AI opportunities and translate business needs into technical solutions.
What kind of projects will the team handle?
The team builds digital-first products and explores how AI can improve operations. Projects include designing Generative AI applications, implementing RAG and agentic workflows, and integrating LLMs into existing business workflows.