Full Stack AI Engineer

Job Description:

Responsibilities

• Build and ship the AI engine: retrieval-augmented generation, context-aware reasoning, evidence citation, and the evaluation harness around it.?
• Architect production-grade agentic applications using LangGraph, AutoGen, Claude Agent SDK, OpenAI Assistants, or your own orchestration layer.?
• Integrate frontier and self-hosted LLMs (Claude, GPT, Gemini, open-weight models) with tools, data, and external systems through MCP and custom connectors.?
• Apply RAG techniques where they actually?help:?vector databases (Pinecone, Chroma, Weaviate, pgvector), hybrid retrieval with ElasticSearch or Solr, BM25 + similarity search, re-ranking.?
• Maintain vendor-agnostic LLM abstractions so providers can be swapped behind a clean interface as enterprise constraints evolve.?
• Design prompt and context engineering frameworks that?optimize?accuracy, repeatability, cost, and latency.?
• Build the backend around it?
• Build modular backends in Python (FastAPI, async patterns) with comfort dipping into TypeScript/Node.js (Fastify, NestJS, Hono, Express) when the stack calls for it—aligned with clean architecture, OOP, SOLID, and domain-driven design.?
• Stand up prototype?front-ends?in Next.js, React, and TypeScript to make ideas tangible?quickly knowing?a front-end specialist will own the polished, production surfaces.?
• Design and ship REST APIs at scale, with OpenAPI/Swagger, webhook patterns, and clean integration boundaries.?
• Work across relational, document, key-value, and graph stores as the problem demands; use event-driven patterns where they fit, not by default.?
• Build enterprise integration surfaces: SSO (OAuth 2.0, OIDC, SAML), RBAC, ingestion pipelines from document and content systems, downstream tool connectors.?
• Implement audit trails, data classification, and change-history patterns where the use case requires them.?
• Ship, Operate, Harden?
• Spin up the infra, write the evals, wire the MCP servers, deploy the agents, and harden the bits that survive contact with real users.?
• Deploy on AWS (or Cloudflare for edge use cases) using containerization (Docker, Kubernetes, ECS, Fargate) or serverless (Lambda)—chosen for fit, not preference.?
• Own CI/CD end-to-end with GitHub Actions or equivalent; manage infrastructure as code with Terraform or Bicep.?
• Treat evals as a first-class discipline: hands-on harnesses, golden datasets, regression rubrics—not theoretical frameworks.?
• Apply engineering practices that hold up in production: TDD, secrets management and rotation, SAST/DAST, structured logging, metrics, tracing.?
• Use AI-assisted development tools (Claude Code, Cursor, GitHub Copilot, Codex) through structured workflows, sub-agents, skills, and templates—with discipline and review.? 

Qualification & Experience

• 4+ years backend and AI engineering experience, production-grade.?
• Hands-on LLM integration experience: orchestration, RAG, vector stores, retrieval tuning, prompt versioning, evals.?
• Hands-on experience with agents, not just prompted models. You have wired tools to a model and let it run multi-step using LangGraph, AutoGen, Claude Agent SDK, OpenAI Assistants, or your own orchestration.?
• Strong Python with OOP, SOLID, 12-factor application development, and microservice architecture. You have built FastAPI services and similar.?
• Comfortable in TypeScript—enough to read it, ship in Node.js when needed, and stand up a Next.js + React prototype to make an idea tangible. You don't need to own polished front-end surfaces.?
• End-to-end implementation experience with vector databases, retrieval pipelines, and eval harnesses.?
• Enterprise integration experience: REST APIs at scale, OAuth/SSO, webhook patterns, ingestion from document and content systems.?
• Cloud-native AWS deployment experience—with Docker, Kubernetes, and GitHub Actions or equivalent. Cloudflare experience a plus.?
• Active, structured use of AI-assisted development tools (Claude Code, Cursor, GitHub Copilot) with demonstrable workflows, sub-agents, skills, and templates.?
• Comfort building for production environments where audit logs, data classification, RBAC, and change history matter.?
• A deep working understanding of how LLMs behave—and where they break—and how to optimize for accuracy, latency, and cost.?
• A no-compromise attitude on clean code, TDD, security, observability, scalability, performance, and cost.?
• A real, recent trail of built things: GitHub, a portfolio, side projects, indie tools, or OSS contributions.?
• A founder's mindset and genuine appetite for ambiguous, high-impact technical challenges.?
• Bachelor's or?Master's in Computer Science, Machine Learning, or a related technical discipline.?
• DevOps depth: end-to-end infrastructure ownership, observability stacks (OpenTelemetry, Application Insights, Datadog), incident response.?
• Public writing, talks, or threads about building with AI.?
• MLOps and model serving experience (BentoML, MLflow, Vertex AI, SageMaker).?
• Streaming and batch ingestion pipelines (Spark, Airflow, Beam, Glue).?
• Eval frameworks: Ragas, DeepEval, Promptfoo, LangSmith, or custom harnesses.?
• Healthcare or life sciences domain exposure.?
• AWS professional certifications or other relevant industry certifications.