- Location
- India - Bangalore · India - Gurgaon
- Type
- Full-time
- Department
- Engineering
- Experience
- 3+ years
- Source
- Workday
Description
We're committed to bringing passion and customer focus to the business.
Key Responsibilities:
•Architect and implement RAG pipelines, agentic AI systems, and LLM-driven applications for enterprise use cases.
•Design and integrate prompt engineering, context management, and knowledge-grounding frameworks to optimize LLM performance.
•Collaborate with data, ML, and software engineering teams to build production-grade GenAI microservices and APIs.
•Evaluate and integrate open-source and proprietary LLMs (e.g., OpenAI, Anthropic, Mistral, Llama, Gemini).
•Design data pipelines for unstructured/structured content ingestion, indexing, and vector retrieval using Milvus, PostgreSQL (pgvector), or similar technologies.
•Define and enforce architecture standards, governance, and best practices for scalable GenAI platforms.
•Conduct PoCs, benchmark model performance, and lead solution transitions from prototype to production.
•Contribute to AI strategy, model lifecycle management, and cost optimization initiatives.
Required Skills and Qualifications:
•Bachelor’s/Master’s degree in Computer Science, AI, Data Engineering, or related field.
•5–8 years of total experience, with at least 3+ years in AI/ML or NLP systems design.
•Proven experience implementing LLM-based solutions, RAG architectures, and prompt orchestration frameworks.
•Strong Python programming skills and familiarity with frameworks like LangChain, LangGraph, LlamaIndex, or Transformers.
•Hands-on knowledge of vector databases (Milvus, Pinecone, Weaviate, Chroma) and knowledge graph systems (Neo4j, RDF).
•Experience deploying and managing AI workloads on cloud platforms (GCP, Azure, AWS).
•Understanding of MLOps/GenAIOps, model evaluation, and observability practices.
•Strong problem-solving, communication, and stakeholder management capabilities.
Preferred Skills
•Experience with multimodal LLMs, agentic reasoning, and tool-using AI agents.
•Exposure to pharma/life sciences or regulated enterprise domains.
•Contribution to open-source AI frameworks or internal AI accelerators.
