Job Summary
We are seeking an Applied AI Agents Engineer with a strong software engineering background to design, implement, and deploy intelligent agent-based systems powered by large language models (LLMs), retrieval-augmented generation (RAG), and orchestration frameworks like LangChain.
The ideal candidate will have 3–5+ years of software engineering experience and at least 1–2 years working in AI / ML or intelligent systems. You will play a key role in building multi-agent workflows , integrating agents into enterprise environments, and deploying them reliably in production.
Experience with orchestration platforms (e.g., aiXplain ) and prompt engineering will be highly valuable.
Key Responsibilities
- Agent Development & Architecture – Design and implement AI agents using LangChain, including reasoning, memory, RAG pipelines, and tool integrations.
- Integration & APIs – Build connectors for databases, APIs, and enterprise systems to extend agent capabilities.
- Scalability & Deployment – Deploy agents to cloud environments, ensuring reliability, security, and performance optimization.
- Optimization & Monitoring – Fine-tune prompts, optimize retrieval workflows, and monitor system performance.
- Collaboration & Documentation – Work closely with AI specialists, data engineers, and domain experts to align solutions with business needs.
Required Skills & Experience
Strong foundation in software engineering (data structures, algorithms, distributed systems, OOP).Proficiency in Python with solid experience in LangChain (agents, chains, RAG pipelines, tool integrations).Good understanding of LLMs, embeddings, and vector databases .3–5+ years of professional software engineering experience.1–2+ years working in AI / ML or intelligent systems.Nice-to-Haves (Plus)
Hands-on experience with aiXplain for agent deployment, orchestration, and monitoring.Familiarity with prompt engineering and evaluation frameworks.Experience building and scaling multi-agent collaboration systems .#J-18808-Ljbffr