About Us:
Chryselys is a Pharma Analytics & Business consulting company that delivers data-driven insights leveraging AI-powered, cloud-native platforms to achieve high-impact transformations.
We specialize in digital technologies and advanced data science techniques that provide strategic and operational insights.
Who we are:
People - Our team of industry veterans, advisors and senior strategists have diverse backgrounds and have worked at top tier companies.
Quality - Our goal is to deliver the value of a big five consulting company without the big five cost.
Technology - Our solutions are Business centric built on cloud native technologies.
Senior GenAI / Agentic Systems Engineer
We are looking for a Senior GenAI / Agentic Systems Engineer to design, build and operate production-grade AI systems that combine LLMs, agents, retrieval, memory and distributed cloud services.
The ideal candidate is a strong software engineer who has moved beyond GenAI experimentation and has hands-on experience taking agentic and AI-powered systems from prototype to reliable production deployments. You will work across agent orchestration, context and state management, RAG, tool integration, distributed services and cloud infrastructure, with a strong focus on reliability, security, scalability and observability.
Key Responsibilities
- Design and develop production-grade GenAI and agentic systems using modern LLM, agent and distributed-systems architectures.
- Build agent workflows incorporating memory, context, state and session management, ensuring agents can maintain the right information across interactions and workflows.
- Design and implement RAG pipelines, including embeddings, chunking, retrieval, reranking and integration with vector databases.
- Develop sophisticated agent orchestration using LangGraph, LangChain and AWS AgentCore.
- Build and integrate tools, APIs and external services using REST, MCP, A2A and event-driven interfaces.
- Design architectures for single-agent and multi-agent systems, including agent-to-agent coordination, delegation and workflow management.
- Develop scalable backend services using Python, TypeScript and/or Java.
- Build cloud-native services on AWS, leveraging managed services and serverless/containerized architectures where appropriate.
- Develop containerized applications and production deployment pipelines using Docker, CI/CD and infrastructure automation.
- Establish robust observability across AI and distributed systems, including logging, metrics, tracing, model/agent behavior and operational monitoring.
- Engineer for reliability, scalability, performance and fault tolerance, including graceful degradation and failure recovery for AI workflows.
- Implement enterprise-grade security and governance, including IAM, encryption, secrets management, access controls and data governance.
- Design systems that appropriately handle sensitive and regulated data, with strong controls around data access, retention, auditability and lineage.
- Collaborate with product, frontend, AI/ML, platform and DevOps teams to translate business requirements into scalable technical solutions.
- Drive technical decisions, architecture evolution, engineering standards and best practices across the GenAI platform.
- Evaluate emerging agent frameworks, protocols, models and infrastructure patterns, and determine where they provide meaningful production value.
Required Experience & Skills
- 5+ years of software engineering experience, with hands-on experience building production GenAI, agentic or distributed systems.
- Strong programming experience in one or more of Python, TypeScript or Java.
- Deep understanding of LLM and agent architectures, including prompting, tool calling, orchestration and structured outputs.
- Strong hands-on experience with agent memory, context management, state management and session management.
- Production experience with RAG, embeddings and vector databases.
- Hands-on experience with LangGraph and/or LangChain.
- Experience with AWS and AWS AgentCore.
- Strong understanding of modern AI interoperability and service protocols, including MCP, A2A and REST APIs.
- Experience designing event-driven and distributed systems.
- Experience with containers, CI/CD and cloud-native deployment practices.
- Strong understanding of observability, including logs, metrics, tracing, alerting and production diagnostics.
- Strong engineering fundamentals around reliability, security, scalability, performance and fault tolerance.
- Practical experience with AWS IAM, encryption, secrets management and data governance.
- Experience designing systems for production workloads rather than purely experimental or proof-of-concept environments.
How to Apply:
Please include your resume and a cover letter detailing why you’re the perfect fit for this role.
Equal Employment Opportunity:
Chryselys is proud to be an Equal Employment Opportunity Employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.
Connect with Us: