15 days ago
Hyderābād, IndiaSenior
Responsibilities
- Design and implement Generative AI solutions from MVP through scalable production systems.
- Build, orchestrate, and optimize multi-agent architectures using LangChain, LangGraph, and AutoGen.
- Integrate AI agents with external tools, APIs, GitHub, and internal or external UI components.
- Develop and deploy Retrieval-Augmented Generation pipelines.
- Use Databricks for scalable data processing, ML model development, and deployment.
- Develop, refine, and evaluate prompts for LLM-based tasks.
- Monitor and optimize the performance and accuracy of AI systems in production.
- Collaborate with cross-functional teams to align AI solutions with business goals.
Requirements
- At least 5 years of AI/ML experience, including at least 2 years focused on Generative AI solutions.
- Strong Python programming skills and proficiency with LangChain, LangGraph, and AutoGen.
- Experience building and orchestrating multi-agent systems.
- A proven track record of taking GenAI MVPs to full-scale production.
- Hands-on experience integrating AI agents with tools and platforms such as GitHub and custom UIs.
- Strong understanding and implementation experience with RAG architecture and prompt engineering.
- Proficiency with Databricks for data and ML workflows.
- Experience with vector databases such as FAISS, Pinecone, or Weaviate is preferred.
- Exposure to Azure, AWS, or GCP is preferred.
- Familiarity with CI/CD for ML pipelines is preferred.
- Strong problem-solving skills and ability to work in a fast-paced, collaborative environment.