> Markdown version of [/jobs/ext/3608922-machine-learning-engineer](https://www.wearedevelopers.com/jobs/ext/3608922-machine-learning-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Machine Learning Engineer - **Company:** Managed Markets Insight & Technology, LLC - **Location:** Yardley, PA, United States (Remote available) - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** Training Data, Amazon Web Services, Amazon Elastic Compute Cloud, Amazon S3, Artificial Neural Networks, Microsoft Azure, Code Review, Computer Programming, Continuous Integration, Data Cleansing, Data Files, Amazon DynamoDB, Python (Programming Language), Machine Learning, Language Modeling, Systems Development Life Cycle, SciPy, Software Engineering, Reinforcement Learning, Flask (Web Framework), Large Language Models, Deep Learning, Generative AI, AWS Lambda, Agentic-AI, Git, Fastapi, Pandas, Build Management, Containerization, Scikit Learn, Integration Tests, Information Technology, Deployment Automation, Machine Learning Operations, Drift Detection, Api Gateway, Model Context Protocol, Data Pipelines, GXP, Docker - **Published:** October 7, 2026 - **Apply:** https://arc.dev/remote-jobs/j/redirect/ppld67ehvx ## About the Role * 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. ## 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.