AI/LLM Engineer — Python, LangChain, RAG, AWS Lambda

• *Project Brief**

We're building AI-powered products, primarily leveraging off-the-shelf LLM APIs, while also partnering with our Applied Science teams to integrate custom models when needed. You'll own end-to-end development of AI features — from prototyping to production — focused on reliability, accuracy, and scalable delivery.

• *Must-Haves
• Strong Python engineering skills and experience delivering production systems
• Hands-on experience building with LLM APIs (OpenAI, Anthropic, etc.) and deploying AI features end-to-end
• Experience with LangChain / LangGraph — including Prompt Engineering, Token Management, and Agent creation with tool-based workflows
• Experience building agentic workflows (tool use, routing, memory, safety/guardrails), ideally with MCP
• Solid understanding of RAG concepts — retrieval, chunking, embeddings, re-ranking, and evaluation
• Practical AWS experience, especially AWS Lambda and serverless architecture patterns
• Backend engineering experience: RESTful API design, webhook integration, JWT, pytest, and observability tools like Sentry
• Experience doing Git repository analysis — understanding large codebases, debugging, refactors, and code health
• Comfortable working in fast-moving product environments with high ownership
• *Nice to Have
• NextJS and TypeScript for frontend components and integration
• AWS CDK for infrastructure-as-code and deployment
• Broader AWS services knowledge: S3, CloudWatch, IAM, API Gateway
• Experience with NoSQL databases
• Experience integrating or serving custom models (inference, model endpoints, monitoring)
• Familiarity with evaluation frameworks (offline tests, human feedback loops, regression suites)
• Strong software engineering fundamentals: testing, CI/CD, observability, performance
• *What You Will Do
• Plan and develop applications that include custom AI components — orchestration, evaluation, tooling, and integrations
• Build intelligent agents using LLMs and the MCP framework to enable context-aware automation and decision-making
• Automate internal workflows and operational processes using Python and AWS Lambda
• Develop and improve RAG-based chatbots to increase response accuracy, grounding, and consistency
• Collaborate with Applied Science teams to productionize custom models and connect them with product systems
• Design and maintain multi-agent AI pipelines, including fallback and graceful degradation strategies for reliability
• *Why You'll Want This Role
• 🚀 First engineering hire — Shape the technical foundation of a rapidly growing product. Your decisions set the standard.
• 📈 Massive market opportunity — Tech debt affects $3 trillion globally, with 41% created by AI. You'll be building the tools that solve it.
• 💡 Real impact — Help companies save millions in development costs through cutting-edge AI/ML solutions.
• 🔝 Direct path to technical leadership — This is a ground-floor opportunity with clear growth into a senior or lead engineering role.
• *Benefits & Compensation
• 💵 $2,000 – $4,500/month — paid in USD, bi-weekly via Deel
• 🌎 Fully Remote — work from anywhere in Latin America
• 📄 Full-time contract with a U.S. company — 6-month initial term, full-time conversion
• 🏖️ Paid PTO — competitive package, grows with tenure
• 🤝 Referral Program — earn a bonus for referring talent that gets hired
• 📈 Be an early employee at a fast-growing startup with direct path to technical leadership
• *To Apply
• *Please send your resume in English.
• *Include The Following
• 🔗 LinkedIn Profile URL (required)
• 💻 GitHub Portfolio — show us your best work (required)
• 🌐 Live Project Examples — applications or tools you've built (encouraged)
• ✉️ Cover Letter — tell us why you're excited about this role (optional but encouraged)
• *About OneSeven Tech**

Founded by James Sullivan, OneSeven Tech is a premier digital product agency serving startups and enterprises. Our clients have collectively raised over $100M in VC, and our enterprise partners include 2,000+ person hospitality groups and NASDAQ-listed companies.

We work fully remote, move fast with 1-week sprints, and focus on elegant solutions to complex problems.