AI Engineer, Agent/Platform Tracks

1 month ago

Remote, India +2 moreMid Level

Responsibilities

Implement specialized pharmacovigilance agents using system prompts, model configuration, tool-use definitions, and defined agent boundaries.
Build and iterate prompt chains for source parsing, field extraction, MedDRA coding suggestions, causality assessment, narrative drafting, and E2B(R3) generation.
Develop deterministic ICH E2B validation, MedDRA hierarchy verification, and regulatory logic constraints alongside LLM outputs.
Create evaluation datasets, annotated ground-truth cases, edge-case libraries, and regression test suites with pharmacovigilance experts.
Develop and maintain Model Context Protocol servers and secure integrations with enterprise applications, APIs, databases, and services.
Run accuracy benchmarks, analyze failure modes, and improve prompts and agent configurations against defined thresholds.
Implement quality-control cross-verification using separate Claude instances, comparison algorithms, and confidence scoring.
Build human-in-the-loop reviewer interfaces and feedback pipelines for accept, modify, and reject decisions.

At least 3 years of software engineering experience, including at least 1 year building applications that use LLM APIs.
Production proficiency in Python.
Experience building and evaluating NLP or LLM-based systems with measurable quality metrics.
Experience with prompt engineering, including system prompts, few-shot examples, chain-of-thought patterns, and structured output formats.
Hands-on experience with LLM orchestration frameworks such as LangChain, LangGraph, or similar tools.
Experience with evaluation pipelines using precision/recall, confusion matrices, and threshold tuning.
Comfort with AWS services including S3, Lambda, and IAM; AWS Bedrock experience is preferred.
Strong written communication for documenting prompt decisions, evaluation results, and agent behavior specifications.
Bachelor's degree in computer science or a related field, or equivalent professional experience.
Preferred experience includes clinical NLP, medical coding or adverse-event extraction, MedDRA or ICD-10, OCR and document processing, and pharma, biotech, CRO, or healthcare IT.

Flexible work environment and space to do one's best work.
Growth and continuous learning opportunities in large language models, prompt engineering, and healthcare AI.
Opportunity to influence clinical research safety systems and work with cross-functional domain and platform teams.

10,000+ employees