21 nov
|
World Business Lenders
|
Quilmes
21 nov
World Business Lenders
Quilmes
Our client is a remote product studio that builds MVPs and custom software for startups and companies past the idea stage.
Clients hire them for a fixed-scope MVP or for a product team billed by the two-week sprint, and the whole team uses AI coding tools every day.They've been at it since **** and were profitable in ****, with a 30% net margin.
After building their own AI systems, they tripled monthly revenue with the same team size.
Clients rate them 4.9 out of 5 in verified reviews, and the startups they build for have raised more than $25M in venture funding.Your RoleYou'll join the team building workflow software for one of the studio's clients: a live product that needs new workflow features while the existing ones keep running.
The client's own engineers commit to the same repo, so every new table, permission and workflow goes in next to code someone else is changing.
The weight is on the server side, from the SQL database on Azure up through the API, and you also build the React and TypeScript screens that sit on top.AI coding tools draft most of the specs, tests and migrations.
You direct them, read every diff line by line, and answer for what merges.
If you'd rather write most of the code by hand, this probably isn't the right seat.You report to the studio's leadership and work day to day with the lead developer and the product manager, who sets the acceptance criteria for each sprint.
Success means delivering four to five features per two-week sprint, each verified before merge, and owning one area end to end (such as the task engine or the legacy migration) without breaking a live feature.You Bring:4+ years building full-stack web applications and releasing them to productionExperience working in a codebase you didn't write, learning its conventions before changing itHands-on work on workflow software where different user roles see different data, with approvals, task queues or state machines and an audit log or versioned historyReact, TypeScript and SQL on Azure, including schema design and migrationsDaily use of Cursor, Claude Code or a similar AI coding tool on production work, with tests and CI behind itClear written and spoken EnglishExperience delivering in fixed-scope sprints with branches, code review and feature flagsBonus Points:Work in a regulated setting such as finance, health or insuranceA migration from a legacy system, with reconciliation and duplicate reviewTime as an outside vendor committing to a client's repoProject rules, custom prompts or agent setups for AI coding tools that your team adoptedSpanish, since the platform is bilingualWhat's Offered:Fully remote contractor role from LATAM, full time at about 40 hours a weekCore hours in US time zones, so your day overlaps with the lead developer and the product managerAn area of the product to own end to end, with your schema designs reviewed by the lead developer and the client's engineersA team where AI-first delivery is already the daily routine, with tests, CI and feature flags as part of the normal processA start in early NovemberInterview Process:Intro Call: 30 minutes with atomic HR on your background and goalsLeadership Screening: A short call, possibly with an async part firstProduct and Developer Conversation:
How you take features from acceptance criteria to mergeTake-Home Test: One feature like the real scope, built and checkedSenior Agentic AI Engineer – AWS (Remote-Global)Spoiler: This is where your next big move begins.What this Journey Looks LikeAt Pearster , we connect talented professionals from around the world with exciting opportunities at international companies.
We are a dynamic, people-oriented team passionate about building meaningful professional connections and creating a positive employee experience.What You'll Lead and BuildDesign, develop, and deploy autonomous AI agents and multi-agent systems using AWS cloud technologies.Lead the architecture and implementation of Agentic AI solutions capable of reasoning, planning, executing tasks, and interacting with external systems.Build and orchestrate AI agents using frameworks such as LangGraph, LangChain, CrewAI, or AWS Strands Agents .
Develop scalable Generative AI applications using Amazon Bedrock, Bedrock Agents, and AWS Lambda .
Integrate Large Language Models (LLMs) into enterprise applications, APIs, databases, and business workflows.Design and implement Retrieval-Augmented Generation (RAG) architectures to enhance AI accuracy and contextual understanding.Build intelligent automation workflows that connect AI agents with internal platforms and third-party services.Develop and optimize prompt engineering strategies, tool calling, memory management, and agent orchestration.Implement secure, scalable, and reliable AI architectures following AWS best practices.Evaluate and optimize LLM performance, latency, accuracy, token consumption, and infrastructure costs.Design and implement monitoring, logging, evaluation, and observability solutions for AI agents in production.Develop APIs, microservices, and backend components to support AI-powered applications.Collaborate with software engineers, cloud architects, product teams, and business stakeholders to identify opportunities for AI-driven automation.Lead technical discussions, define architectural standards, and provide guidance on Agentic AI implementation.Create prototypes and proof-of-concept solutions to validate emerging AI technologies and business use cases.Ensure AI solutions follow security, data privacy, governance, and responsible AI principles.Troubleshoot complex technical challenges and continuously improve AI agent reliability and performance.Document solution architectures, technical decisions, and implementation best practices.What You Bring to the TableAdvanced English (C1) - excellent written and verbal communication skills.5+ years of experience in Software Engineering, Cloud Engineering, AI/ML Engineering, or related technical roles.2+ years of hands-on experience with Generative AI, LLM-based applications,
or AI agent development.Strong expertise in AWS cloud architecture , particularly Amazon Bedrock, AWS Lambda, S3, IAM, API Gateway, and related services.Proven experience designing and implementing Agentic AI systems , including autonomous agents, tool calling, and multi-agent orchestration.Hands-on experience with LangGraph, LangChain, CrewAI, AWS Strands Agents , or similar agentic AI frameworks.Advanced Python programming skills , including backend development, APIs, and integration with AI services.Strong understanding of Large Language Models (LLMs) , including Claude, Amazon Nova, and other foundation models available through Amazon Bedrock.Experience implementing RAG architectures , vector databases, embeddings, and semantic search.Familiarity with vector databases such as Amazon OpenSearch, Pinecone, FAISS, or similar technologies.Experience with prompt engineering, context management, model evaluation, and LLM optimization.Solid knowledge of software architecture, distributed systems, microservices, and scalable cloud-native applications .
Experience integrating AI solutions with REST APIs, enterprise platforms, and third-party applications.Familiarity with Docker, CI/CD pipelines, Git, Infrastructure as Code, and modern deployment practices.Understanding of AI security, access control, data privacy, and responsible AI practices.Experience deploying, monitoring, and maintaining production-grade AI applications .
Strong analytical thinking, debugging, and complex problem-solving skills.Ability to lead technical decisions and design end-to-end AI architectures with minimal supervision.Excellent communication skills and ability to explain complex AI concepts to technical and non-technical stakeholders.Strong ownership mindset, autonomy, adaptability, and ability to work in fast-paced international environments.AWS certifications, particularly AWS Certified Solutions Architect - Professional or AWS Certified Machine Learning Engineer - Associate .
Experience with Amazon Bedrock AgentCore and advanced AWS agent orchestration capabilities.Knowledge of Model Context Protocol (MCP) and agent-to-agent communication protocols.Experience with LLMOps, MLOps, and automated AI evaluation frameworks.Familiarity with Kubernetes, Amazon EKS, or serverless architectures.Experience building enterprise-grade AI solutions in regulated or high-security environments.Previous experience leading AI initiatives, mentoring engineers, or defining technical architecture standards.Benefits that Move you Forward.We're here to amplify your brilliance, not contain it.Work from anywhere with true flexibility and freedom.Earn in USD with compensation that matches your expertise.Recharge confidently with dedicated paid time off.Advance your career with fully covered international certifications.Access coworking spaces worldwide whenever you want a professional setup.Strengthen your English and expand your general reach.Connect and have fun with activities that unite our international team.Feel appreciated with personalized gifts and a thoughtful welcome kit.Grow our community and earn through our referral program.At Pearster, your journey matters, and we're here to help you go further than you imagined.
#J-*****-Ljbffr
📌 Senior Ai Product & Decision Systems Lead (Remote) (Quilmes)
🏢 World Business Lenders
📍 Quilmes