AI / GenAI Engineer
Hyderabad, India · Onsite · Full-Time
Job description
Build and evaluate AI applications that connect language models with useful enterprise information. Translate business needs into testable prototypes and maintainable services, with attention to retrieval quality, privacy and responsible use.
Key responsibilities
- Develop Python services that integrate language models with enterprise applications.
- Build retrieval-augmented generation workflows, including document preparation and retrieval.
- Create evaluation datasets and measure response quality, relevance and failure cases.
- Implement input validation, access controls, logging and appropriate human review.
- Investigate latency, reliability and cost across model and retrieval workflows.
- Document experiments, technical decisions and deployment requirements with delivery teams.
Skills and experience
- Practical Python development experience and familiarity with APIs.
- Understanding of language models, embeddings and retrieval-based application patterns.
- Experience testing model outputs against defined acceptance criteria.
- Familiarity with Azure services and cloud application development.
- Ability to communicate limitations and collaborate with engineering and business stakeholders.
Additional experience
- Exposure to vector search, orchestration frameworks and automated evaluation.
- Experience applying secure development and monitoring practices to AI applications.
Career enquiries
Use the career enquiry form on this page and include the role title, your relevant skills and preferred location in your message.