Sr. Associate Software Engineer

Overview

Early-career engineering role on an AI engineering team building LLM-based systems, focused on evaluating whether an AI/LLM system's output is correct and modelling extracted information as structured knowledge (entities and relationships).

What you'll do

• Build and extend LLM evaluation harnesses, including golden datasets, precision/recall/F1, calibration, and LLM-as-judge scoring.
• Design and work with knowledge graphs, including entity-relationship modelling, graph traversal/queries, and embeddings-based similarity and retrieval.
• Build GenAI/LLM pipelines in Python, including prompting, RAG, and structured output.
• Write clean, tested code, collaborate with senior engineers, and document your work.
• Act in accordance with and as a good steward of Duck Creek Technologies mission, vision, and core values.

What you'll need

• B.Tech/M.Tech with an AI/ML specialization, or CS/IT with strong, demonstrable AI coursework/projects.
• 0 to 2 years of experience.
• Strong Python fundamentals and solid grasp of data structures and algorithms.
• Working understanding of LLM fundamentals: prompting, embeddings, RAG, and basic evaluation concepts.
• A maintained personal GitHub profile with at least one substantive AI/LLM project (academic or personal), not a cloned tutorial. Resume and GitHub profile link must be shared; applications without a working GitHub link showing original project work will not be considered.

Nice to have

• Exposure to evaluation frameworks/metrics for generative AI (e.g. Ragas, DeepEval, or a self-built LLM-judge approach).
• Exposure to knowledge graphs / graph data structures (NetworkX, Neo4j, RDF/OWL, or a well-reasoned custom graph model in a project).
• Any agent framework (LangChain/LangGraph or similar), vector databases, any cloud platform, REST API basics (FastAPI/Flask).

Details

• Location: Bengaluru, India. Role is aligned to a specific location; candidate is expected to reside within reasonable proximity to that location.
• Ways of working: flexible-first. May initially be remote, subject to business needs, and may transition to a hybrid arrangement including working from a designated office on a schedule set by the leader.
• Company reserves the right to modify work arrangement, location expectations and in-person requirements.
• AI tools are not permitted during interviews.