Data Scientist

Role & responsibilities

Data Scientist Python, Generative AI, RAG & NLP

Roles and Responsibilities:

• Develop and deploy production-ready Generative AI and LLM applications using Python, integrating models such as OpenAI, Anthropic, and Gemini.
• Design and optimize RAG pipelines, including document chunking, embeddings, vector databases, semantic search, and reranking.
• Build agentic AI workflows with tool calling, planning, and multi-agent orchestration.
• Develop scalable REST APIs and microservices, ensuring performance, concurrency, and reliability.
• Implement AI evaluation, groundedness checks, hallucination reduction, and regression testing.
• Optimize AI application latency, token usage, and operational costs; implement observability and secure data-handling practices.
• Lead technical architecture reviews, code reviews, mentoring, and collaboration with stakeholders to deliver AI solutions to production.

Key requirements: 812 years of experience, with strong production-level Generative AI/LLM development expertise.

Work details: Hyderabad (Madhapur), 4 days a week from the client office; 12 PM–9 PM shift; 6–12 months contractual engagement.