Senior Full Stack AI Engineer
Job Description
Senior Full Stack AI Engineer
We're building a core product that uses LLMs and RAG pipelines to turn psychological assessment data into high-quality, clinician-grade narratives. We're hiring a senior, hands-on full stack engineer to architect and ship a production-grade RAG microservice that ingests assessment data, retrieves from manuals/knowledge bases, and returns accurate narratives for customers. This role moves fast, operates in ambiguity, and delivers real product impact.
Responsibilities
Architect, design, and implement a production-grade RAG microservice for ingestion, indexing, retrieval, and augmented generation of psychological assessment data.
Build scalable, secure Python-backed microservices and APIs that integrate with existing React frontend flows.
Integrate and manage LLMs, vector stores, embeddings, and retrieval components to ensure accurate, context-aware narrative generation.
Validate and QA outputs with domain data to ensure narratives use correct assessment information and classifications.
Establish and enforce best practices for reliability, observability, CI/CD, and Git workflows for production deployments.
Ship end-to-end features quickly: prototype, iterate with product/CEO/Head of Engineering, and deliver customer-facing releases.
Collaborate closely with Head of Engineering and CEO to align architecture with product vision and scaling needs.
Document system designs, operational runbooks, and provide handoff materials for the team.
Mentor and unblock junior engineers through code reviews and practical guidance as needed.
Requirements (Must-haves)
Strong Python proficiency with demonstrated history of building backend services and microservices in production.
Proven experience designing and shipping RAG pipelines, LLM integrations, or similar retrieval-augmented LLM systems.
Solid system and API design skills with examples of production-grade architecture for scale and reliability.
Practical experience with embeddings, vector stores (or equivalent), and prompt/response engineering for LLMs.
Track record of delivering end-to-end product features that integrate AI/LLM outputs into consumer or enterprise-facing apps.
Demonstrated outcome orientation: drives ambiguous projects to fast, tangible results with minimal supervision.
Strong communication skills: can translate fuzzy product vision into clear technical plans for founders and non-engineers.
Comfortable operating in a fast-moving startup environment with limited guardrails and frequent pivots.
Nice to Have
Hands-on React/front-end experience and previous work integrating AI outputs into UI flows.
Prior experience working with healthcare or regulated data (e.g., assessments, HIPAA-aware systems).
Familiarity with production observability tools, monitoring, and security practices for AI services.
Experience with common vector DBs (e.g., Pinecone, Milvus, Weaviate), or cloud-native alternatives.
Compensation & Benefits
U$D 2000 / 2500
Unlimited Paid Time off
Team / Reporting
Reports to: CEO / Head of Engineering
Works closely with: Head of Engineering, CEO, product stakeholders, and a small engineering team.
Location / Work Type
Remote-friendly; Only Latin America candidates considered
Regular working hours preferred 9-–6 ET Time
How to Apply
Send your updated resume to