AI Engineer – Agent-Oriented LLM Workflows
We’re building the future of AI-driven agent workflows—and we want you to help lead the way. As an AI Engineer, you'll architect, deploy, and optimize advanced LLM-based agent systems that can interact, reason, and deliver business value at scale.
You’ll collaborate closely with data engineers and product stakeholders to bring multi-agent orchestration frameworks, retrieval-augmented generation (RAG) pipelines, and real-world deployment strategies to life.
Start date: ASAP
Contract type: Contractor - Indefinite
Work hours: Monday to Friday, 7.30 am to 4.30 pm PST - 100% Remote
️ What You’ll Be Doing
- Design and deploy AI agent workflows using LangChain and LangFlow.
- Implement MCP (Model Context Protocol) to standardize agent-tool-data interactions.
- Build Agent-to-Agent (A2A) systems for orchestrated task automation across domains (e.g., reporting, validation, marketing agents).
- Define production-ready agentic pipelines with robust logging and resilience.
- Benchmark and select the most suitable LLMs (GPT-4, Claude, LLaMA) based on latency, cost, and task complexity.
- Design RAG architectures using vector databases to enhance response quality and domain alignment.
- Optimize prompts, model parameters, and outputs for consistency and accuracy.
- Containerize and deploy agents using Docker and Kubernetes.
- Set up real-time monitoring and performance evaluation dashboards for agent behavior and LLM output validation.
- Collaborate on CI/CD pipelines and implement production guardrails.
- Work closely with Data Engineering to ensure scalable and secure data pipelines for agents.
- Lead architectural discussions and share best practices in agent orchestration.
- Document workflows, configurations, and operational standards for internal teams.
✅ What You Need to Succeed
Must-haves
- 3+ years of experience in AI/ML engineering or LLM-based systems.
- Hands-on experience in production with:
- LangChain, LangFlow, or similar orchestration tools
- Vector databases (e.g., Pinecone, Weaviate, FAISS)
- Python + ML frameworks (e.g., PyTorch, TensorFlow)
- Docker, Kubernetes, and CI/CD systems (GitHub Actions, Jenkins)
- Proven experience deploying agentic systems and building pipelines involving LLMs.
- Strong understanding of LLM prompt engineering, context management, and tool/agent interoperability.
- Comfortable with Linux environments and cloud platforms (AWS/GCP/Azure).
Nice-to-haves
- Experience with LangGraph, AutoGen, CrewAI, or other multi-agent orchestration frameworks.
- Prior work on chatbots, autonomous agents, or RAG pipelines.
- Familiarity with AI security, compliance, or ethical risk mitigation.
- Contributions to open-source AI projects or academic publications.
Our Recruitment Process
Here’s what to expect from our candidate-friendly interview process:
Initial Interview – 60 minutes with our Talent Acquisition Specialist
Culture Fit – 30 minutes with our Team Engagement Manager
- Technical Assessment - Python, LangChain, LLM
Final Stage – 60 minutes with the Hiring Manager (Technical Interview)
Why Join Launchpad?
We believe that great work starts with great people. At Launchpad, we offer:
Fully remote work with hardware provided
Global team experience with clients in [regions]
Competitive USD compensation
Training and learning stipends
Paid Time Off (vacation, personal, study)
♂️ A culture that values autonomy, purpose, and human connection
✨ Apply now and let’s architect what’s next together.
Originally posted on Himalayas
Apply Now