Software Engineer AI/ML, LLMs & Agentic Systems

• Design, develop, and deploy RAG (Retrieval-Augmented Generation) systems integrating vector databases, embedding models, and custom retrievers.
• Architect and fine-tune custom LLMs (via parameter-efficient tuning, LoRA, or domain-specific training).
• Create and manage agentic AI workflows multi-step reasoning systems powered by tools such as LangChain, CrewAI, or OpenDevin.
• Implement prompt engineering and prompt-chaining techniques to optimize LLM behavior and reliability.
• Build and maintain scalable LangChain-based applications that interact with databases, APIs, and business systems.
• Collaborate with data scientists to design and deploy ML/AI pipelines leveraging AWS, Azure, or GCP cloud infrastructure.
• Develop, test, and optimize APIs that integrate AI reasoning and autonomous decision-making capabilities.
• Monitor and improve model performance, latency, and token efficiency using observability tools like LangFuse, Phoenix, or OpenDevin dashboards.
• Document architectural decisions, experiment metrics, and system flows for technical transparency.
  

• 4+ years in Python software development, with strong understanding of asynchronous programming and API design.
• Solid experience deploying LLM applications using frameworks like LangChain, LlamaIndex, or Haystack.
• Proficiency working with vector databases (FAISS, Pinecone, Weaviate, Milvus, Qdrant) and embedding models (OpenAI, sentence-transformers, Cohere, HuggingFace).
• Experience designing autonomous agent systems, connecting LLMs with Python functions, tools, or APIs.
• Strong command of prompt engineering, including contextual grounding, role prompting, and few-shot examples.
• Familiarity with RAG pipeline architecture (retriever, ranker, generator layering).
• Understanding of custom model fine-tuning techniques (RLHF, LoRA, QLoRA, PEFT).
• Experience with cloud-based model deployment (AWS Sagemaker, Azure ML, Vertex AI).
• Working knowledge of AI observability, evaluation frameworks (LangFuse, Traceloop, Phoenix).
  

• Experience building autonomous agents using frameworks like LangGraph, CrewAI, OpenDevin, or AutoGPT.
• Experience deploying multi-agent collaboration systems or tool-using AI.
• Background in knowledge graph integration, context window optimization, and embedding search tuning.
• Contribution to open-source AI/LLM projects.
• Strong understanding of data governance, AI ethics, and model interpretability.
  

Languages:

Frameworks:

Databases:

Cloud:

AI Stack:

Architecture:

• Opportunity to build next-generation agentic AI systems used in real-world enterprise settings.
• Collaborative environment focused on innovation in RAG, LLMs, and autonomous agents.
• Flexible work arrangements and continuous learning culture.
• Access to cutting-edge compute environments and AI tools.
  

Our Culture & Values

At Calpion, were not just a company were a dynamic culture fueled by six core values: Agile, Collaborative, Innovative, Fun, Inclusive, and Passionate. These values drive our every move:

• Agile:

  We thrive on change, adapting swiftly to new challenges.

• Collaborative:

  Together, we achieve greatness through teamwork and diverse perspectives.

• Innovative:

  We push boundaries, constantly exploring new ideas and solutions.

• Fun:

  Laughter and camaraderie make our workplace a joyous one.

• Inclusive:

  Diversity is our strength, ensuring every voice is heard and valued.

• Passionate:

  We approach every task with dedication and enthusiasm.

Join us at Calpion and be part of a culture thats not just about work innovation, growth, and making an impact.