142. Senior AI Engineer – LLM and Agent Systems

<h2 data-start="224" data-end="311">We’re looking for a<strong> Senior AI Engineer – LLM and Agent Systems to join Source Meridian</strong></h2> <h2 data-start="318" data-end="347"><strong data-start="322" data-end="347">About Source Meridian</strong></h2> <p data-start="673" data-end="799">Source Meridian is a development software company that works to solve the industry’s most challenging problems in healthcare practices. We are laser focused on specific technologies in the healthcare and life science industries: Healthcare technology, artificial intelligence, and healthcare interoperability.</p> <p data-start="673" data-end="799">&nbsp;</p> <h2><strong>About the Role</strong></h2> <p>AI Engineer with hands-on experience in building production-grade artificial intelligence systems using large language models (LLMs), agentic frameworks, and modern data infrastructure. The ideal candidate designs, develops, and deploys intelligent applications that leverage LLM orchestration, retrieval-augmented generation (RAG), and memory-managed architectures.</p> <p>&nbsp;</p> <h2 data-start="1253" data-end="1272">What You’ll Do</h2> <p>&nbsp; &nbsp; &nbsp; &nbsp; • &nbsp; &nbsp; &nbsp; Design and implement agentic workflows using LangGraph and LangChain, including multi-step reasoning, tool usage, and human-in-the-loop patterns.<br>&nbsp; &nbsp; &nbsp; &nbsp; •&nbsp; &nbsp; &nbsp; &nbsp;Integrate LLMs (OpenAI, Anthropic, Google Vertex AI, open-source models) via REST APIs and SDKs into scalable backend services.<br>&nbsp; &nbsp; &nbsp; &nbsp; • &nbsp; &nbsp; &nbsp; Build and maintain RESTful APIs (FastAPI) to serve AI-powered functionality to frontends and external consumers.<br>&nbsp; &nbsp; &nbsp; &nbsp; • &nbsp; &nbsp; &nbsp; Architect and manage vector database solutions (Milvus) for semantic search and retrieval-augmented generation (RAG).<br>&nbsp; &nbsp; &nbsp; &nbsp; •&nbsp; &nbsp; &nbsp; &nbsp;Design context engineering strategies, including prompt templates, dynamic context window management, token optimization, and context compression techniques.<br>&nbsp; &nbsp; &nbsp; &nbsp; • &nbsp; &nbsp; &nbsp; Implement short-term memory (conversational buffers, sliding windows, summary memory) and long-term memory (persistent vector stores, knowledge graphs, user profile stores) using MongoDB&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; and vector databases.<br>&nbsp; &nbsp; &nbsp; &nbsp; • &nbsp; &nbsp; &nbsp; Store and manage structured and unstructured data in MongoDB, designing schemas that support conversation history, user state, and agent checkpoints.</p> <p>&nbsp; &nbsp; &nbsp; &nbsp; • &nbsp; &nbsp; &nbsp; Evaluate and improve the quality of LLM responses through prompt engineering, few-shot examples, guardrails, and automated evaluation pipelines.<br>&nbsp; &nbsp; &nbsp; &nbsp; • &nbsp; &nbsp; &nbsp; Collaborate with DevOps teams to containerize and deploy AI services using Docker, Kubernetes, and CI/CD pipelines on AWS or GCP.</p> <p>&nbsp;</p> <p data-start="673" data-end="799">&nbsp;</p> <h2 data-start="2174" data-end="2202">Required Qualifications</h2> <ul> <li data-start="2205" data-end="2263">Strong command of Python (3+ years)</li> <li data-start="2205" data-end="2263">Demonstrable experience with LangChain and LangGraph (graph-based agent orchestration, state management, conditional edges, parallel execution).</li> <li data-start="2205" data-end="2263">Solid understanding of the fundamentals of LLMs: tokenization, embeddings, temperature/sampling, RAG.</li> <li data-start="2205" data-end="2263">Hands-on experience with vector databases and embedding models for semantic search and retrieval pipelines.</li> <li data-start="2205" data-end="2263">Experience designing and consuming REST APIs; knowledge of authentication.</li> <li data-start="2205" data-end="2263">Proficiency in MongoDB (document modeling, aggregation pipelines, indexing strategies).</li> <li data-start="2205" data-end="2263">Understanding memory architectures for conversational AI: summary memory, entity memory, and long-term persistent stores.</li> <li data-start="2205" data-end="2263">Familiarity with context engineering: token budget management, hybrid search (sparse + dense).</li> <li data-start="2909" data-end="3041">English level: B2 or higher</li> </ul> <h2 data-start="3048" data-end="3065">&nbsp;</h2> <h2 data-start="3048" data-end="3065">Nice to Have</h2> <p>&nbsp; &nbsp; &nbsp; &nbsp; • &nbsp; &nbsp; &nbsp; &nbsp;Experience with assessment frameworks (RAGAS, Langfuse (LangSmith), customized assessments).<br>&nbsp; &nbsp; &nbsp; &nbsp; • &nbsp; &nbsp; &nbsp; Experience with streaming responses.</p> <p data-start="2589" data-end="2675">&nbsp;</p> <h2 data-start="3216" data-end="3237"><strong data-start="3220" data-end="3237">What We Offer</strong></h2> <p data-start="3239" data-end="3414">✔ Permanent contract<br data-start="3259" data-end="3262">✔ Learning and continuous growth environment 🚀<br data-start="3309" data-end="3312">✔ Benefits package focused on health and well-being 🎉<br data-start="3366" data-end="3369">✔ Competitive salary based on experience 💰</p> <p data-start="3416" data-end="3470">&nbsp;</p> <p data-start="3416" data-end="3470">📍&nbsp;<strong data-start="3419" data-end="3470">Apply only if you reside in Colombia or Ecuador</strong></p> <p data-start="3416" data-end="3470">&nbsp;</p> <p data-start="3477" data-end="3605">At&nbsp;<strong data-start="3480" data-end="3499">Source Meridian</strong>, you’ll be part of a high-impact&nbsp;<strong data-start="3533" data-end="3548">tech-health</strong>&nbsp;company, building products that truly make a difference.</p> <p data-start="3607" data-end="3716">If you meet the profile — or know someone who might be interested —&nbsp;<strong data-start="3675" data-end="3689">apply now!</strong></p> <p data-start="3607" data-end="3716">We’d love to meet you 💬</p>