About the company
We are a young and fast-growing recruiting company with five years of experience working across Latin America and the United States. We partner closely with teams and founders to help them build strong, high-impact teams through recruitment, outsourcing, and team-building services.
Our culture is built on effective communication, trust, and transparency. We believe great work happens when people feel heard, supported, and empowered to grow. Today, our team is made up of more than 80 professionals working across different projects throughout the region, collaborating remotely and learning from each other every day.
About the role
We’re looking for an AgentCore Platform Engineer to join a dedicated delivery pod building an internal agent platform on AWS Bedrock AgentCore for a global life sciences organization.
You’ll work alongside the client’s engineers to build the agent-facing layer of the platform: how agents run, manage memory, work together, and safely interact with the internal systems the business already relies on.
Each engineer will have a primary focus in one of two areas while working closely across both:
Agent Runtime & Orchestration: Build runtime patterns, memory strategies, orchestration, multi-agent handoffs, and reference implementations that other teams can reuse.
Gateway, Tools & Integrations: Turn internal APIs, Lambda functions, and legacy systems into governed agent tools through AgentCore Gateway, including MCP server development.
Production experience with Bedrock AgentCore is valuable but not required. Strong AWS fundamentals and real hands-on experience building LLM agents with established agent frameworks are equally relevant.
This is a named-team engagement, meaning the person proposed for the role will be the person who joins the project.
Responsibilities
- Define how agents are structured, packaged, and deployed on AgentCore Runtime, including sessions, state management, error handling, and timeouts.
- Design short-term and long-term memory strategies using AgentCore Memory and guide engineering teams on when to use each approach.
- Build orchestration patterns for planning, tool use, supervisor/worker architectures, and multi-agent handoffs, with clear boundaries and fallback mechanisms.
- Expose internal REST APIs, Lambda functions, and legacy services as governed agent tools through AgentCore Gateway.
- Work with OpenAPI specifications and Lambda targets to standardize tool onboarding.
- Design and build Model Context Protocol (MCP) servers for systems requiring custom integrations, with clear tool definitions and schemas.
- Implement authentication and authorization for agents and tools using AgentCore Identity, OAuth, IAM, and related security patterns.
- Work with system owners to safely integrate legacy and on-premises systems, considering rate limits, data mapping, authentication, and failure scenarios.
- Build production-quality reference agents, starter kits, and reusable patterns that other engineering teams can adopt.
- Establish standards and repeatable processes for adding, versioning, reviewing, and maintaining agent tools.
- Implement evaluation, Bedrock Guardrails, contract tests, and safety checks to ensure predictable behavior before production deployment.
- Create documentation and run walkthroughs to help other teams adopt the platform.
- Support engineering teams during onboarding and help troubleshoot implementation challenges.
- Contribute to technical decisions around agent architecture, integrations, security, and platform standards.
Requirements
- 5+ years of software engineering experience, with strong hands-on experience in Python
- TypeScript is a plus.
- Hands-on experience building LLM-based agents using at least one agent framework such as Strands Agents, LangGraph, LangChain, CrewAI, OpenAI Agents SDK, or LlamaIndex.
- Practical experience with LLM tool/function calling and handling model outputs.
- Strong AWS fundamentals, including IAM, Lambda, API Gateway, containers, DynamoDB, S3, VPC connectivity, and Secrets Manager.
- Experience designing and consuming REST APIs and OpenAPI specifications.
- Understanding of authentication patterns such as OAuth 2.0 and OIDC.
- Understanding of agent memory, RAG, and context management trade-offs.
- Deep hands-on strength in at least one of the two focus areas, combined with working knowledge of the other.
- Ability to write clean, well-tested code that other engineers can understand, maintain, and reuse.
- Strong communication skills and the ability to explain and teach technical patterns to other engineering teams.
- Previous consulting experience.
Nice to have
- Hands-on experience with Amazon Bedrock AgentCore, particularly Runtime, Memory, Gateway, or Identity.
- Experience building or operating MCP servers in production or real-world environments.
- Experience with multi-agent systems in production, including observability and failure handling.
- Experience integrating enterprise or legacy systems, or working with API management platforms such as MuleSoft, Apigee, or Kong.
- Experience with LLM evaluation tools and methodologies.
- Experience working in pharma, life sciences, healthcare, or other regulated industries with strict data access controls.
- Previous experience or connections within the Life Sciences industry.
Benefits
- People First culture
- Referral Program
- Free access to streaming platforms
- Free access to Spotify Premium
- GYM discount
- Travel discount
- E-Learning discount
- Birthday-day gift
- Points Program