Hybrid
Full-Time
Bengaluru, Karnataka
India
Skills
Python (Programming Language)
Large Language Models (LLM)
Neuro-Linguistic Programming (NLP)
Machine Learning
About the Role
About the Role:
We are looking for a GenAI / ML Engineer to join our R&D team and work on cutting-edge applications of LLMs in biomedical data processing. In this role, you'll help build and scale intelligent systems that can extract, summarize, and reason over biomedical knowledge from large bodies of unstructured text, including scientific publications, EHR/EMR reports, and more.
You’ll work closely with data scientists, biomedical domain experts, and product managers to design and implement reliable GenAI-powered workflows — from rapid prototypes to production-ready solutions. This is a highly strategic role as we continue to invest in agentic AI systems and LLM-native infrastructure to power the next generation of biomedical applications.
Key Responsibilities:
Build and maintain LLM-powered pipelines for entity extraction, ontology normalization, Q&A, and knowledge graph creation using tools like LangChain, LangGraph, and CrewAI.
Fine-tune and deploy open-source LLMs (e.g., LLaMA, Gemma, DeepSeek, Mistral) for biomedical applications.
Define evaluation frameworks to assess accuracy, efficiency, hallucinations, and long-term performance; integrate human-in-the-loop feedback.
Collaborate cross-functionally with data scientists, bioinformaticians, product teams, and curators to build impactful AI solutions.
Stay current with the LLM ecosystem and drive adoption of cutting-edge tools, models, and methods.
Qualifications:
2–3 years of experience as an ML engineer, data scientist, or data engineer working on NLP or information extraction.
Strong Python programming skills and experience building production-ready codebases.
Hands-on experience with LLM frameworks and tooling (e.g., LangChain, HuggingFace, OpenAI APIs, Transformers).
Familiarity with one or more LLM families (e.g., LLaMA, Mistral, DeepSeek, Gemma) and prompt engineering best practices.
Strong grasp of ML/DL fundamentals and experience with tools like PyTorch, or TensorFlow.
Ability to communicate ideas clearly, iterate quickly, and thrive in a fast-paced, product-driven environment.
Good to Have (Preferred but Not Mandatory)
Experience working with biomedical or clinical text (e.g., PubMed, EHRs, trial data).
Exposure to building autonomous agents using CrewAI or LangGraph.
Understanding of knowledge graph construction and integration with LLMs.
Experience with evaluation challenges unique to GenAI workflows (e.g., hallucination detection, grounding, traceability).
Experience with fine-tuning, LoRA, PEFT, or using embeddings and vector stores for retrieval.
Working knowledge of cloud platforms (AWS/GCP) and MLOps tools (MLflow, Airflow etc.).
Contributions to open-source LLM or NLP tooling
We are looking for a GenAI / ML Engineer to join our R&D team and work on cutting-edge applications of LLMs in biomedical data processing. In this role, you'll help build and scale intelligent systems that can extract, summarize, and reason over biomedical knowledge from large bodies of unstructured text, including scientific publications, EHR/EMR reports, and more.
You’ll work closely with data scientists, biomedical domain experts, and product managers to design and implement reliable GenAI-powered workflows — from rapid prototypes to production-ready solutions. This is a highly strategic role as we continue to invest in agentic AI systems and LLM-native infrastructure to power the next generation of biomedical applications.
Key Responsibilities:
Build and maintain LLM-powered pipelines for entity extraction, ontology normalization, Q&A, and knowledge graph creation using tools like LangChain, LangGraph, and CrewAI.
Fine-tune and deploy open-source LLMs (e.g., LLaMA, Gemma, DeepSeek, Mistral) for biomedical applications.
Define evaluation frameworks to assess accuracy, efficiency, hallucinations, and long-term performance; integrate human-in-the-loop feedback.
Collaborate cross-functionally with data scientists, bioinformaticians, product teams, and curators to build impactful AI solutions.
Stay current with the LLM ecosystem and drive adoption of cutting-edge tools, models, and methods.
Qualifications:
2–3 years of experience as an ML engineer, data scientist, or data engineer working on NLP or information extraction.
Strong Python programming skills and experience building production-ready codebases.
Hands-on experience with LLM frameworks and tooling (e.g., LangChain, HuggingFace, OpenAI APIs, Transformers).
Familiarity with one or more LLM families (e.g., LLaMA, Mistral, DeepSeek, Gemma) and prompt engineering best practices.
Strong grasp of ML/DL fundamentals and experience with tools like PyTorch, or TensorFlow.
Ability to communicate ideas clearly, iterate quickly, and thrive in a fast-paced, product-driven environment.
Good to Have (Preferred but Not Mandatory)
Experience working with biomedical or clinical text (e.g., PubMed, EHRs, trial data).
Exposure to building autonomous agents using CrewAI or LangGraph.
Understanding of knowledge graph construction and integration with LLMs.
Experience with evaluation challenges unique to GenAI workflows (e.g., hallucination detection, grounding, traceability).
Experience with fine-tuning, LoRA, PEFT, or using embeddings and vector stores for retrieval.
Working knowledge of cloud platforms (AWS/GCP) and MLOps tools (MLflow, Airflow etc.).
Contributions to open-source LLM or NLP tooling