AI Engineer II / III

Kriya Therapeutics•Morrisville, NC

2d•Hybrid

About The Position

The AI Engineer designs, builds, and operates agentic AI systems, retrieval infrastructure, and data pipelines that help realize Kriya's AI strategy. This role’s responsibilities include developing custom AI agents, retrieval-augmented generation (RAG) pipelines, and MCP connectors that make Kriya's data accessible to AI tools. As a member of Kriya's Applied Computation & AI (ACAI) team, the AI Engineer partners closely with stakeholders across the organization to ship production-grade AI systems quickly while meeting Kriya's security, compliance, and governance standards. This role requires strong software engineering fundamentals, hands-on experience with modern agentic AI and cloud/data infrastructure, and the judgment to translate ambiguous scientific and business needs into reliable systems.

Requirements

Bachelor's degree in Computer Science, Engineering, or a related field. Advanced degree preferred.
3-7+ years of experience as a software, ML, or AI engineer (level based on depth of experience with agentic systems and scope of technical leadership). An equivalent combination of education and experience is acceptable.
Hands-on experience building agentic AI systems / multi-step LLM workflows using frameworks such as LangGraph, AWS Bedrock / AgentCore, CrewAI, or similar.
Experience building RAG systems, including chunking, embeddings, vector databases, and retrieval evaluation.
Strong Python engineering skills, including API development and integration (MCP, REST).
Experience with AWS cloud services (e.g., Lambda, S3, Bedrock, IAM) and Databricks or similar platforms, with solid data engineering fundamentals (ETL pipelines, data modeling, structured and unstructured data).
Experience with LLMs and prompt engineering / evaluation practices.
Experience with version control (Git) and collaborative development practices (CI/CD, code review, testing).
Life sciences, biotech, or pharma experience preferred, including familiarity with GxP-adjacent data governance and lab or manufacturing information systems (e.g., ELN/LIMS).
Scientific curiosity and analytical mindset, with the ability to translate ambiguous stakeholder needs into technical solutions.
Excellent written and verbal communication for working with technical and non-technical stakeholders.
Self-directed with ability to manage multiple projects independently in a fast-moving, resource-constrained environment.

Responsibilities

Design, build, and deploy agentic AI systems and LLM-based tools, including specialized, on-demand AI agent-contractors (e.g., scientific review, competitive intelligence, experimental design, manufacturing analysis) and custom AI skills and plugins, using orchestration frameworks such as LangGraph, AWS Bedrock / AgentCore, or similar.
Build, evaluate, and maintain retrieval-augmented generation (RAG) pipelines and vector search capabilities over Kriya's internal data, exposing that data to AI tools via MCP connectors and unified APIs.
Develop production-grade data pipelines connecting Kriya's datalake to AI applications, ensuring architecture, access patterns, and governance meet downstream AI requirements.
Apply strong software engineering practices — testing, CI/CD, version control, observability, and monitoring — to build reliable, secure, and maintainable AI systems.
Collaborate cross-functionally across functions such as CMC, Clinical, Corporate Strategy, Legal, and Finance to implement high-value opportunities for agentic AI and computational solutions, translating scientific and business needs into technical designs.
Provide technical leadership on agent architecture and AI system design, model best practices for the team, and mentor junior team members.