Sr. Associate Software Engineer
Duck Creek Technologies
Bengaluru, Karnataka, India0–2 yrs2h agovia LinkedIn
This job at a glance
- Who can apply
- Freshers and up to 2 years · B.Tech / B.E. or M.Tech
- Must know
- PythonGitMachine learningFlaskFastAPIREST APIs
- Nice to have
- LLMsData structures & algorithms
- Work
- On-site in Bengaluru
- Pay
- Not stated by the employer.
- Skill demand
- Python41%Git30%Machine learning10%Flask1%of 116 similar fresher jobs posted in India this week
- Listed
- 30 Oct 2026 · still open
Sign in free to see which of these skills your resume already shows.
About the Role
Duck Creek Technologies is seeking early-career engineers to join an AI engineering team focused on building LLM-based systems. This role involves evaluating the correctness of AI/LLM outputs and modeling extracted information as structured knowledge for trusted querying and reasoning.
Key Responsibilities
- Build and extend LLM evaluation harnesses, including golden datasets, precision/recall/F1, calibration, and LLM-as-judge scoring.
- Design and work with knowledge graphs, focusing on entity-relationship modeling, graph traversal/queries, and embeddings-based similarity and retrieval.
- Build GenAI/LLM pipelines in Python, incorporating prompting, RAG, and structured output.
- Write clean, tested code, collaborate with senior engineers, and document work.
- Act in accordance with Duck Creek Technologies' mission, vision, and core values.
Requirements & Tech Stack
- Strong Python fundamentals.
- Solid grasp of data structures & algorithms.
- Working understanding of LLM fundamentals: prompting, embeddings, RAG, basic evaluation concepts.
- A maintained personal GitHub profile with at least one substantive AI/LLM project (academic or personal).
Qualifications
- B.Tech/M.Tech with an AI/ML specialization, or CS/IT with strong, demonstrable AI coursework/projects.
- 0 to 2 years of experience.
Good 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 (e.g., NetworkX, Neo4j, RDF/OWL, or a custom graph model).
- Experience with any agent framework (LangChain/LangGraph or similar).
- Experience with vector databases.
- Experience with any cloud platform.
- Basic understanding of REST API principles (FastAPI/Flask).