Accountabilities:

As an AI Engineer focused on agent and platform development, you will be responsible for designing, implementing, and improving AI-driven workflows that enhance data processing accuracy, efficiency, and reliability. You will work closely with engineering and domain teams to create scalable AI capabilities while ensuring quality, security, and compliance.

• Design and implement specialized AI agents by developing system prompts, configuring model parameters, defining tool usage, and establishing agent boundaries.
• Build and optimize prompt workflows for document processing, information extraction, coding recommendations, assessment logic, and structured output generation.
• Develop deterministic validation layers that complement AI outputs through business rules, quality checks, and regulatory logic.
• Create and maintain evaluation datasets, including benchmark cases, edge scenarios, and regression testing frameworks.
• Develop and maintain Model Context Protocol (MCP) servers to connect AI agents with enterprise applications, APIs, databases, and internal services.
• Implement secure integrations, authentication mechanisms, testing processes, and reliable tool interactions for AI systems.
• Analyze AI performance through accuracy benchmarks, failure analysis, and continuous improvements to prompts and agent configurations.
• Build human-in-the-loop feedback mechanisms to improve AI performance through structured reviews and continuous learning cycles.

Requirements:

The ideal candidate will have strong software engineering fundamentals combined with practical experience building AI and LLM-powered applications. You should be comfortable working with emerging AI technologies, evaluating model performance, and collaborating with cross-functional teams in a fast-moving environment.

• 3+ years of software engineering experience, including at least 1 year developing applications powered by LLM APIs such as Anthropic, OpenAI, or equivalent platforms.
• Strong proficiency in Python with experience building production-grade applications.
• Hands-on experience with prompt engineering, including system prompts, few-shot examples, structured outputs, and AI workflow optimization.
• Experience with LLM orchestration frameworks such as LangChain, LangGraph, or similar technologies.
• Knowledge of evaluation methodologies for NLP or LLM systems, including quality metrics, benchmarking, and performance tuning.
• Familiarity with AWS services such as S3, Lambda, and IAM, with experience using AWS Bedrock considered a plus.
• Strong documentation and communication skills, with the ability to explain technical decisions and AI behaviors clearly.
• Ability to collaborate effectively with engineering teams, domain specialists, and business stakeholders.
• Bachelor’s degree in computer science, engineering, or a related field, or equivalent professional experience.

Preferred qualifications include:

• Experience working with healthcare, clinical, medical NLP, or regulated technology environments.
• Familiarity with medical terminology systems such as MedDRA or ICD-10.
• Experience with document processing technologies, including OCR, PDF extraction, or data ingestion pipelines.
• Exposure to AI applications in pharma, biotechnology, healthcare IT, or clinical research.

Benefits:

• Opportunity to work on innovative AI solutions with real-world healthcare impact.
• Exposure to advanced technologies including large language models, AI agents, and automation frameworks.
• Flexible work environment with remote options available.
• Continuous learning and professional development opportunities.
• Collaboration with multidisciplinary teams across technology and healthcare domains.
• Opportunity to contribute to next-generation AI platforms and intelligent systems.
• Supportive environment focused on growth, innovation, and meaningful contributions.