- Experience
- 4+ yrs
- Salary
- —
- Openings
- 1
- Posted
- hace 1 hora
- Work mode
- In office
- Education
- B.Tech / B.E.
- Eligibility
- Candidates holding a Bachelor of Technology (B.Tech) or Bachelor of Engineering (B.E.) degree in any specialized stream can apply.
- Resume
- Required to apply
Where you'll work
Sign in to tell us what does and doesn't work for you here — it sharpens every match we show you.
Job description
About the Role
We are looking for a knowledgeable Generative AI Engineer to architect, create, and deploy advanced AI-driven applications utilizing Large Language Models (LLM). The position demands proficiency in building LLM-based solutions, applying Retrieval-Augmented Generation (RAG) methods, backend API development, and establishing AI services within cloud infrastructures.
Key Responsibilities
- Designing and implementing AI applications leveraging LLM frameworks like LangChain and LlamaIndex.
- Developing and enhancing RAG solutions through vector databases.
- Creating robust and scalable backend APIs and microservices to support AI functionalities.
- Applying prompt engineering techniques, function/tool call integration, and agent-based workflow development.
- Deploying and maintaining AI services using containerization (Docker), orchestration (Kubernetes), CI/CD pipelines, and cloud platforms.
- Enhancing model inference efficiency by optimizing caching, batching, and prompts.
- Cooperating with cross-functional teams—product, platform, engineering—to deliver enterprise-grade AI solutions.
- Adhering to security standards, governance policies, responsible AI practices, and monitoring production AI systems.
Required Qualifications and Skills
- Proficiency in Python programming.
- Experience in backend API and microservices development.
- Hands-on expertise with LLM-based application development.
- Familiarity with frameworks such as LangChain, LlamaIndex, OpenAI, and Azure OpenAI.
- Practical knowledge of RAG pipeline implementation and vector database integration.
- Advanced skill in prompt engineering and development of AI agents.
- Competence in Docker, Kubernetes, cloud platforms, and CI/CD methodologies.
- Understanding of techniques for fine-tuning models, inference optimization, and deployment of LLM solutions.
Preferred Qualifications
- Experience with LLMOps or MLOps tools and monitoring systems.
- Awareness of AI security, privacy, compliance matters, and Responsible AI frameworks.
- Proven track record of deploying AI solutions within large enterprise settings.
Experience Required
A minimum of four years in software engineering roles, including at least two years focused on Generative AI, LLM implementations, or AI application development.
Eligibility
Applicants must hold a B.Tech or B.E. degree in any engineering specialization.
Minimum education
Bachelor's Degree