ML / Data Science Engineer

Job Description

Experience: 2 + years Expected Notice Period: 30 Days Shift: (GMT+05:30) Asia/Kolkata (IST) Opportunity Type: Office (Pune) Placement Type: Full Time Permanent position Must have skills required: Airflow, LLMs, NLP, Statistical Modeling, Predictive Analysis, Forecasting, Python, SQL, MLFlow, pandas, Scikit-learn, XgBoost As an ML / Data Science Engineer at Anervea, youll work on designing, training, deploying, and maintaining machine learning models across multiple products. Youll build models that predict clinical trial outcomes, extract insights from structured and unstructured healthcare data, and support real-time scoring for sales or market access use cases. Youll collaborate closely with AI engineers, backend developers, and product owners to translate data into product features that are explainable, reliable, and impactful. Key Responsibilities Develop and optimize predictive models using algorithms such as XGBoost, Random Forest, Logistic Regression, and ensemble methods Engineer features from real-world healthcare data (clinical trials, treatment adoption, medical events, digital behavior) Analyze datasets from sources like ClinicalTrials.gov, PubMed, Komodo, Apollo.io, and internal survey pipelines Build end-to-end ML pipelines for inference and batch scoring Collaborate with AI engineers to integrate LLM-generated features with traditional models Ensure explainability and robustness of models using SHAP, LIME, or custom logic Validate models against real-world outcomes and client feedback Prepare clean, structured datasets using SQL and Pandas Communicate insights clearly to product, business, and domain teams Document all processes, assumptions, and model outputs thoroughly Technical Skills Required : Strong programming skills in Python (NumPy, Pandas, scikit-learn, XGBoost, LightGBM) Experience with statistical modeling and classification algorithms Solid understanding of feature engineering, model evaluation, and validation techniques Exposure to real-world healthcare, trial, or patient data (strong bonus) Comfortable working with unstructured data and data cleaning techniques Knowledge of SQL and NoSQL databases Familiarity with ML lifecycle tools (MLflow, Airflow, or similar) Bonus: experience working alongside LLMs or incorporating generative features into ML Bonus: knowledge of NLP preprocessing, embeddings, or vector similarity methods Personal Attributes : Strong analytical and problem-solving mindset Ability to convert abstract questions into measurable models Attention to detail and high standards for model quality Willingness to learn life sciences concepts relevant to each use case Clear communicator who can simplify complexity for product and business teams Independent learner who actively follows new trends in ML and data science Reliable, accountable, and driven by outcomesnot just code Bonus Qualities : Experience building models for healthcare, pharma, or biotech Published work or open-source contributions in data science Strong business intuition on how to turn models into product decisions