Staff Software Engineer

Skip to main content Go to homepage Menu Saved Jobs (0) EN Filter Languages English English Canadian Français Canadian French View all jobs Search Jobs Find jobs for Location Radius miles 5 miles 15 miles 25 miles 35 miles 50 miles Search Staff Software Engineer Bengaluru, Karnataka Apply now Save job Posted 07/13/2026 Job reference 14047 Experience level Experienced Hire Job category Engineering & Technology Line of business Asset Mgmt At Moody's, we unite the brightest minds to turn today’s risks into tomorrow’s opportunities. We do this by striving to create an inclusive environment where everyone feels welcome to be who they are—with the freedom to exchange ideas, think innovatively, and listen to each other and customers in meaningful ways. Moody’s is transforming how the world sees risk. As a global leader in ratings and integrated risk assessment, we’re advancing AI to move from insight to action—enabling intelligence that not only understands complexity but responds to it. We decode risk to unlock opportunity, helping our clients navigate uncertainty with clarity, speed, and confidence. If you are excited about this opportunity but do not meet every single requirement, please apply! You still may be a great fit for this role or other open roles. We are seeking candidates who model our values: invest in every relationship, lead with curiosity, champion diverse perspectives, turn inputs into actions, and uphold trust through integrity. Skills and CompetenciesPossesses more than 7 years of overall experience with 5+ years of hands-on experience in data engineering, with advanced proficiency in Python for building scalable, production-grade systems.3+ years developing production RAG pipelines, including semantic and hierarchical chunking, advanced query rewriting, and multi-query strategies.Proficient in hybrid search techniques combining dense retrieval, BM25, filtering, and reranking; skilled in optimizing context windows and balancing latency, recall, and precision trade-offs.Well-versed in retrieval evaluation methodologies such as NDCG, MRR, recall@k, precision, and domain-specific assessments.Demonstrated experience using Vector DBs (OpenSearch/Elasticsearch, Pinecone, Weaviate, Qdrant, Milvus, etc.), including index tuning, sharding/replication, distributed search, and low-latency retrieval optimizationSkilled in selecting and adapting embedding models (SBERT, OpenAI, Cohere, Voyage) to domain-specific needs, optimizing for quality, latency, memory footprint, and cost in large-scale real-time applications.Knowledgeable in advanced retrieval techniques such as similarity metrics, multi-vector/late interaction architectures, cross-encoder rerankers, and conducting embedding evaluations on domain datasets.Well-versed in utilising essential libraries such as Pandas/Polars, NumPy, Pydantic and AI framework/libraries like LangChain, LangGraph, etc.Experience in designing and orchestrating large-scale data pipelines with tools such as AirFlow, Prefect, or Dagster for both ETL/ELT, supporting streaming and batch processes.Experience using distributed computing frameworks such as Spark, Ray, or Dask and implement monitoring systems to ensure data quality.Experience in integrating API both REST/GraphQL based. Implementing Caching to improve the performance using REDIS/MemCachedWell versed with implementing data privacy and security mechanisms like PII/redaction; secrets/access control.Experience in Financial/Structured Finance domain and PDF/OCR/layout/table extraction is preferrableEducation Bachelor’s, Master’s, or PhD degree in Computer Science,...