Engineering Manager
- Closed
- US Company | Large ( employees)
- LATAM (100% remote)
- 6+ years
- Long-term (40h)
- SaaS Tools
- Full Remote
Required skills
- Python
- AWS
- LLM
- Qdrant
Requirements
Must-haves
- 6+ years of software development experience
- 3+ years of experience as a Manager or a Tech Lead
- Experience with LLM-based and agentic AI systems in production (Chatbots, RAG, semantic search, summarization, agentic workflows)
- Proficiency with Python
- Proficiency with AWS
- Proficiency with orchestration libraries (LangChain, LlamaIndex, OpenAI/Bedrock APIs)
- Experience with vector databases and hybrid search technologies (Qdrant, OpenSearch, Pinecone, etc.)
- Proven ability to manage technical projects and stakeholders in agile environments
- Experience leading teams through ambiguity, iteration, and tight feedback loops
- Strong people leadership skills, including mentorship, system design guidance, and raising engineering maturity
- Bias toward action and continuous learning—delivering quickly while maintaining quality and robust infrastructure
- Strong communication skills in both spoken and written English
Nice-to-haves
- Startup experience
- Strong understanding of GenAI tech stack (Python, LangChain, LlamaIndex, Qdrant, OpenSearch, AWS)
- Experience optimizing system performance and supporting team troubleshooting
- Bachelor’s Degree in Computer Engineering, Computer Science, or equivalent
What you will work on
- Lead execution and ensure engineering quality across agentic AI systems powering multi-step Copilot workflows
- Build and scale Retrieval-Augmented Generation (RAG) pipelines and hybrid search infrastructure
- Develop LLM-based personalization and summarization for legislative, regulatory, and media-related content
- Design and maintain AI evaluation frameworks measuring accuracy, latency, and user trust
- Create developer productivity tools enabling fast and reliable AI delivery
- While participating in architectural discussions and hands-on initiatives, the main focus will be on leading the team, driving technical execution, and establishing repeatable delivery patterns for AI-first development
- Expected outcomes within the first 12 months:
- Deliver production-ready GenAI-powered features—Copilot workflows, summarization, agentic systems, and hybrid search—aligned with roadmap priorities and supported by measurable sprint progress
- Hire and onboard at least one engineer while fostering a culture of ownership, learning, and continuous improvement
- Build strong partnerships with Product, Design, and GTM teams, translating technical insights into clear input for planning and ensuring engineering outcomes align with user and business goals
- Expected outcomes within the first 24 months:
- Define and evolve the long-term engineering strategy for GenAI capabilities, integrating emerging technologies (e.g. multi-agent systems, fine-tuning, improved RAG methods) into production
- Strengthen technical expertise across the stack (Python, LangChain, LlamaIndex, vector databases like Qdrant or OpenSearch, AWS infrastructure) and support troubleshooting and optimization efforts
- Improve team velocity through better code reviews, enhanced test coverage, and automated deployments, leading retrospectives that yield measurable process improvements
- Communicate effectively by clarifying assumptions, escalating blockers promptly, and maintaining transparency throughout project delivery
- Mentor engineers and contribute to a positive, inclusive, and collaborative culture through initiatives such as onboarding support or guild leadership
- Support recruitment efforts by conducting interviews, evaluating candidates, and helping identify long-term technical needs