NLP Engineer
Zimmer Biomet1 day ago
Bengaluru, IndiaMid Level / Senior
Responsibilities
- Design and build retrieval-augmented generation pipelines with chunking, embeddings, vector storage, retrieval tuning, and reranking.
- Develop production prompt and context engineering, agent and tool-calling workflows, and generative-system evaluation harnesses.
- Build document and text extraction pipelines for named entity recognition, classification, summarization, relation extraction, and structured data generation.
- Handle scanned PDFs, OCR output, tables, multi-column layouts, inconsistent templates, and human-in-the-loop review requirements.
- Select, fine-tune, and evaluate language and embedding models; create labeled datasets, define baselines, and conduct error analysis.
- Write tested, reviewed, documented Python and deploy, monitor, and support NLP services on Azure.
- Monitor quality drift, cost, latency, and production performance while documenting design decisions, evaluation results, and limitations.
- Collaborate with platform and data engineers, security and privacy teams, quality and regulatory colleagues, and business stakeholders.
Requirements
- Bachelor’s or Master’s degree in computer science, computational linguistics, data science, engineering, mathematics, or a related field, or equivalent practical experience.
- Three to five years of experience building NLP or machine-learning systems, including at least one production system serving real users.
- Experience building production LLM applications using retrieval-augmented generation and prompt engineering.
- Experience extracting structured information from unstructured documents at scale and quantitatively measuring model or pipeline quality.
- Strong Python skills and familiarity with PyTorch or TensorFlow, Hugging Face Transformers, spaCy, scikit-learn, and pandas.
- Experience with LLM application frameworks such as LangChain or LlamaIndex and vector retrieval technologies such as Azure AI Search, FAISS, pgvector, or Pinecone.
- Understanding of transformer architectures, tokenization, embeddings, fine-tuning, semantic search, and embedding-index management.
- SQL and experience working with data at scale, plus software engineering fundamentals including Git, automated testing, code review, and CI/CD.
- Cloud experience, preferably Microsoft Azure, including deploying and operating services rather than only developing notebooks.
- Experience working directly with non-technical stakeholders to define ambiguous business problems and technical scope.
- Preferred qualifications include regulated-industry experience, clinical or regulatory text experience, SNOMED, MedDRA, ICD, Azure Document Intelligence, MLOps, responsible AI, open-source or publication contributions, and Global Capability Center experience.
Benefits
- Flexible working environment with two days working from home and three days working from the office.
- Development opportunities, employee resource groups, location-specific total rewards, wellness incentives, and recognition and performance awards.
- Bangalore-based role supporting global stakeholders across Zimmer Biomet.
Categories
About Zimmer Biomet
Zimmer Biomet designs and manufactures orthopedic implants, surgical instruments, and digital/robotic systems used by hospitals and surgeons for joint replacement and musculoskeletal care. It generates revenue by selling implants, consumables, and related software and services worldwide, including the ROSA robotic surgery platform. Founded in 1927 and headquartered in Warsaw, Indiana, the public company trades on the NYSE and sells in more than 100 countries.