AI Engineer – Cloud

This is a fully remote position, open to applicants in Latin America.

📋 Description

• Design, develop, and sustain AI systems that transform customer interactions and uploaded documents into reliable, verifiable cost estimates.

• Construct and manage LangGraph agents, which encompass ReAct retrieval sub-agents, tailored middleware, Pydantic-typed graph state, and streaming workflows.

• Take ownership of retrieval quality from start to finish through collection routing, LLM-driven metadata filters, similarity thresholds, query rewriting, semantic chunking, and citation tracking.

• Integrate AWS Bedrock, OpenAI, and self-hosted vLLM behind a unified abstract interface.

• Oversee platform API services, relational and domain-knowledge data stores, vector storage, and AI workflow observability/tracing.

• Set the technical direction for the AI workstream.

• Conduct design and code reviews.

• Provide mentorship to engineers.

• Collaborate with product stakeholders and make strategic roadmap trade-offs.

• Analyze production traces to enhance agent reliability, latency, LLM cost efficiency, retrieval grounding, and estimation/sizing accuracy.

⛳️ Requirements

• Bachelor’s degree in Computer Science, Software Engineering, Data Science, or Mathematics.

• At least 6 years of progressive software engineering experience.

• Over 1 year of experience in building production LLM-powered or machine learning systems, including agents, RAG, or prompt/evaluation pipelines.

• Demonstrated ability to deliver in a fast-paced environment.

• Availability to overlap with U.S./Eastern-Time business hours for client meetings.

• Expert-level production software engineering skills.

• Proficiency in creating LLM-powered systems, agents/orchestration, retrieval-augmented generation, and prompt/evaluation pipelines.

• In-depth understanding of retrieval and grounding, embeddings and vector search, multi-model integration, and cost/latency optimization.

• Familiarity with the cost-estimation / Work Breakdown Structure domain, or the capacity to quickly learn intricate domains.

• Ability to analyze complex, non-deterministic AI behavior from production traces and deliver scalable, well-tested solutions under time constraints.

• Exceptional communication skills for conveying technical and model behavior concepts clearly to non-technical and client stakeholders.

• Confidence in participating in live U.S./ET client meetings and maintaining disciplined asynchronous written communication across time zones.

• Proven capability to make critical, time-sensitive decisions with limited information.

• High level of ownership, motivation, action-oriented mindset, and a willingness to go above and beyond.

• Strong leadership abilities.

• Optional: Master’s degree in Computer Science, Machine Learning, or AI.

• Optional: Relevant cloud or machine-learning certification.

• Optional: Experience with self-hosted model inference, observability and tracing tools, clean layered service architecture, internal AI tooling/automation, cloud-platform expertise, agent-reliability patterns, document ingestion across various formats, evaluation/benchmark frameworks, regression fixtures, direct U.S.-based client experience, mentoring, design reviews, technical direction, roadmap trade-offs, and high-growth environment experience.

🏝️ Benefits

• Flexible working arrangements.

• Opportunities for long-term development.

• A collaborative, trust-based, and quality-focused work environment.

• Autonomy accompanied by accountability.

• A chance to influence architecture, technical direction, and standards.

• Mentoring and professional growth alongside experienced engineers.