Machine Learning Engineer

Description

About Norstella At Norstella our mission is simple to help our clients bring life-saving therapies to market quicker—and help patients in need. Founded in 2022 but with history going back to 1939 Norstella unites best-in-class brands to help clients navigate the complexities at each step of the drug development life cycle —and get the right treatments to the right patients at the right time. Each Organization (Citeline Evaluate MMIT Panalgo The Dedham Group) Delivers Must-have Answers For Critical Strategic And Commercial Decision-making. Together Via Our Market-leading Brands We Help Our Clients Citeline - accelerate the drug development cycle Evaluate - bring the right drugs to market MMIT - identify barrier to patient access Panalgo - turn data into insight faster The Dedham Group - think strategically for specialty therapeutics By combining the efforts of each organization under Norstella we can offer an even wider breadth of expertise cutting-edge data solutions and expert advisory services alongside advanced technologies such as real-world data machine learning and predictive analytics. As one of the largest global pharma intelligence solution providers Norstella has a footprint across the globe with teams of experts delivering world class solutions in the USA UK The Netherlands Japan China and India.

Job Description

We are seeking an ML Engineer to build and ship the machine learning and LLM systems behind MMIT’s market access intelligence. MMIT a Norstella company is the market access arm of the group—helping life sciences clients understand and improve how their therapies are covered from formulary status and prior authorization to covered lives and benefit design. In this role you will pair strong production ML engineering with real market access fluency and above all deep hands-on command of large language models (LLMs)—how they work and how to tune them. You will turn US payer and coverage data into predictive analytics plain-language answers and agentic workflows that commercial and market access teams can act on. The role sits at the intersection of applied AI engineering and market access domain expertise. You will work across cross-functional teams of data scientists machine learning engineers data engineers and market access subject matter experts (SMEs)—translating coverage and access requirements into models and agents adapting LLMs to internalize the desired end-to-end behavior and operationalizing them reliably and compliantly in production.

Responsibilities

Design build and deploy machine learning and LLM-based models—including systems that interpret payer coverage formulary status and prior authorization / step therapy requirements—into production collaborating closely with data engineers and data scientists. Adapt and tune LLMs for market access tasks—including fine-tuning prompt and instruction design retrieval augmentation and parameter/behavior optimization so models internalize the desired end-to-end behavior across the target task surface area edge cases and known failure modes. Design build and continuously refine fine-tuning datasets consisting of input/output pairs that demonstrate gold-standard behavior partnering with market access SMEs to shape schema vocabulary and the definition of “what good output looks like.” Run iterative model experiments diagnose where a model is failing design targeted data or prompt changes to close those gaps and measure the impact of each change with human-in-the-loop SMEs. Build and operationalize evaluation harnesses enable SME graders to run eval rounds and translate their feedback into concrete model dataset and tool-call-layer improvements. Design and build agentic workflows on domain-grounded language models including surfacing authoritative coverage and access data to LLMs via MCP (Model Context Protocol) servers and consuming them into agentic pipelines. Create secure AWS SageMaker endpoints and Lambdas and define request/response formats and the appropriate AWS service per use case to operationalize models as scalable services. Develop and maintain secure robust and scalable data pipelines for market access and coverage data feeding training fine-tuning and inference workloads. Implement MLOps best practices—including data and model drift checks monitoring and troubleshooting—to ensure data quality accuracy and reliability integrate these checks and stages (e.g. automated deployment following successful re-training or re-tuning) within the CI/CD pipeline. Maintain provenance licensing and compliance documentation for datasets and models ensuring training data and workflows meet GxP regulatory and intellectual property standards expected in life sciences and market access settings. Conduct proofs of concept for novel market access capabilities and contribute to Norstella’s knowledge base and taxonomy work.

Qualifications

Bachelor’s or graduate degree in computer science STEM life sciences or equivalent professional experience. At least 3 years of professional experience in machine learning engineering with a focus on deploying secure and robust models in production. Hands-on experience with Generative AI especially LLMs and agents throughout the entire software development lifecycle (SDLC)—including a strong working understanding of how LLMs behave and how to tune them (fine-tuning prompt/instruction design and evaluation). Experience creating MCPs and consuming them into agentic workflows. Strong programming skills in Python with experience in libraries such as scikit-learn pandas scipy click and flask and/or FastAPI. Good to have - Experience working with Market Access data and/or understanding of therapeutic areas from a clinical standpoint. Experience with the AWS ecosystem specifically with services like SageMaker and Lambda. Experience working with US market access data—such as payer coverage formulary status prior authorization / step therapy criteria covered lives and benefit design—and a good understanding of the drug and procedure codes used in access analytics (NDCs J-codes HCPCS ICD-10). Experience working with and statistically analyzing large and complex data sets including data cleaning and preprocessing. Good understanding of the software development lifecycle and practices including Git and version control code reviews and functional unit and integration testing. Excellent problem-solving skills and the ability to work independently. Excellent communication skills especially between technical and non-technical teams. Shift timing - 4PM to 1AM IST Good To Have

Skills

Knowledge of non-market-access life sciences data assets such as EMR medical and pharmacy claims and clinical trials data. Developing evaluating deploying and monitoring algorithms and models from proof-of-concept experimental stages through to production in a reproducible auditable GxP-compliant manner. AWS services beyond SageMaker and Lambda such as S3 EC2 ECS ECR API Gateway DynamoDB and Bedrock. CI/CD processes especially as applied to ML operations (MLOps) preferably with Azure DevOps. Advanced machine learning techniques (neural networks ensemble learning reinforcement learning etc.) and the ability to implement them in Python. Docker or other containerization technologies. Fast-paced novel development cycles. Our Guiding Principles For Success At Norstella 01 Bold Passionate Mission-First 02 Integrity Truth Reality 03 Kindness Empathy Grace 04 Resilience Mettle Perseverance 05 Humility Gratitude Learning

Benefits

Health Insurance Provident Fund Reimbursement of Certification Expenses Gratuity 24x7 Health Desk Norstella is an equal opportunity employer. All job applicants will receive equal treatment regardless of race creed color religion alienage or national origin ancestry citizenship status age physical or mental disability or handicap medical condition sex (including pregnancy and pregnancy-related conditions) marital or domestic partner status military or veteran status gender gender identity or expression sexual orientation genetic information reproductive health decision making or any other protected characteristic as established by federal state or local law. Sometimes the best opportunities are hidden by self-doubt. We disqualify ourselves before we have the opportunity to be considered. Regardless of where you came from how you identify or the path that led you here- you are welcome. If you read this job description and feel passion and excitement we’re just as excited about you. All legitimate roles with Norstella will be posted on Norstella’s job board which is located at norstella.com/careers. If a role is not posted on this job board a candidate should assume the role is not a legitimate role with Norstella. Norstella is not responsible for an application that may be submitted by or through a third-party and candidates should proceed with extreme caution if a third-party approaches them about an open role with Norstella. Norstella will never ask for anything of value or any type of payment during or as part of any recruitment interview or pre-hire onboarding process. If you are aware of or have reason to believe a job posting purportedly for a role with Norstella is fraudulent or otherwise not authorized by Norstella please contact the Company using the following email address ApplicationHelp@norstella.com.