- Experience
- 5–11 yrs
- Salary
- —
- Openings
- 1
- Posted
- hace 5 días
- Work mode
- In office
- Education
- B.Tech
- Eligibility
- Candidates possessing a Bachelor of Technology (B.Tech), Bachelor of Engineering (B.E.), Bachelor of Computer Applications (B.C.A.), or Bachelor of Science (B.Sc.) degree in any field are eligible to 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
Infosys, a global leader in next-generation digital services and consulting, is looking for a seasoned Generative AI Engineer with extensive knowledge in Generative AI technologies, Agent Frameworks, RAG (Retrieval-Augmented Generation), and Model Context Protocol (MCP). This full-time position is based in Hyderabad, India, with a preference for immediate joiners or candidates available on short notice. You will be responsible for designing and implementing intelligent, scalable AI solutions that leverage large language models (LLMs), multi-agent orchestration, and effective context management.
Key Responsibilities
- Create and develop applications powered by generative AI utilizing advanced LLM ecosystems.
- Construct and enhance Retrieval-Augmented Generation pipelines for AI solutions that understand context effectively.
- Design and manage Agentic AI systems through frameworks such as LangChain, AutoGen, and CrewAI.
- Implement multi-agent workflows with efficient orchestration techniques.
- Employ Model Context Protocol to manage prompts and context dynamically.
- Integrate LLMs with enterprise software, APIs, and database systems for seamless operations.
- Refine prompts and continuously assess model performance based on accuracy, latency, and cost metrics.
- Guarantee the security, scalability, and reliability of deployed AI systems.
- Collaborate effectively with cross-disciplinary teams including data engineers, product managers, and DevOps professionals.
- Keep up-to-date with the latest tools, frameworks, and best practices in Generative AI technologies.
Required Skills and Qualifications
- Proven experience developing applications based on Generative AI and large language models.
- Hands-on expertise with RAG architectures using vector databases like FAISS, Pinecone, or Weaviate.
- Strong familiarity with popular Agent Frameworks such as LangChain, AutoGen, or CrewAI.
- Experience in building and orchestrating multi-agent AI systems.
- Understanding of Model Context Protocol or similar context-management strategies.
- Proficient in Python programming language.
- Work experience with OpenAI, Azure OpenAI, or comparable LLM APIs.
- Knowledge of prompt engineering and evaluation methodologies.
- Experience in REST API development and microservices architecture.
Preferred Qualifications
- Experience with model fine-tuning and embedding techniques.
- Familiarity with vector search databases and semantic search implementations.
- Exposure to cloud computing platforms such as AWS, Azure, or Google Cloud Platform.
- Awareness of ML Ops and LLM Ops tools and frameworks.
- Experience building streaming pipelines and real-time AI applications.
- Understanding of data privacy regulations and AI governance principles.
Eligibility
Applicants should hold a B.Tech or B.E. degree in any specialization, or a B.C.A. or B.Sc. degree in any specialization.
Minimum education
Bachelor's Degree