Website:
samanvitha.ai
Job details:
Company Description
Samanvitha AI Labs is a pioneering artificial intelligence company dedicated to delivering innovative AI-driven products and services. Our mission is to leverage AI to solve complex challenges, optimize business processes, and drive digital transformation across diverse industries. With a strong focus on scalability, innovation, and user-centric design, we create advanced machine learning models, intelligent automation tools, and custom AI applications that address unique client needs. Our team of experts is committed to pushing the boundaries of AI to empower businesses with greater efficiency, productivity, and competitive advantages.
Role Description
Are you obsessed with the next frontier of AI? We are looking for an AI Engineer focused on developing AI agents to join our team and move beyond traditional prompt engineering. You will be responsible for architecting, developing, and deploying autonomous agent systems that can plan, reason, and execute complex workflows to solve real-world business problems.
In this role, you won't just be "chatting" with LLMs—you’ll be building the infrastructure that allows them to take action.
Key Responsibilties
- Design & Architecture: Build robust, scalable, and secure agentic workflows using frameworks like LangChain, LangGraph, AutoGen, or CrewAI.
- Tool Orchestration: Develop custom tools, APIs, and plugins that enable agents to interact with external databases, web services, and internal software ecosystems.
- Reasoning & Planning: Implement and fine-tune reasoning patterns (Chain-of-Thought, ReAct, Tree-of-Thought) to improve agent reliability and goal-oriented decision-making.
- Evaluation & Testing: Create rigorous evaluation pipelines (using frameworks like RAGAS or Phoenix) to measure agent performance, hallucination rates, and task success metrics.
- Deployment: Work with DevOps to deploy agentic systems in production environments, ensuring high availability, latency management, and cost-efficiency.
- Collaboration: Partner with product managers and subject matter experts to identify high-impact use cases where agentic automation can drive measurable ROI.
Qualifications
- Experience: 2+ years of experience in Software Engineering or AI/ML development.
- AI Frameworks: Proven experience building with major LLM frameworks (LangChain, LlamaIndex, AutoGen, etc.).
- LLM Proficiency: Deep understanding of transformer architectures, prompt engineering, fine-tuning, and RAG (Retrieval-Augmented Generation) patterns.
- Engineering Stack: Strong proficiency in Python and familiarity with modern web backends (FastAPI/Flask).
- Systems Thinking: Ability to decompose complex business processes into modular, autonomous steps.
- Data Handling: Experience working with vector databases (Pinecone, Milvus, Weaviate, or Chroma).
What we value?
- Curiosity: You keep up with the daily deluge of research papers on agentic memory, multi-agent collaboration, and reasoning.
- Pragmatism: You know when to use a simple script and when to deploy a complex autonomous agent.
- Ownership: You are comfortable debugging non-deterministic systems where "it works on my machine" is rarely the case.
Why join us?
- Cutting-Edge Tech: You will be working at the absolute bleeding edge of AI development.
- Impact: You’ll be building systems that fundamentally change how our company (and our customers) operate.
- Growth: We provide a budget for learning, conferences, and experimentation.
Click on Apply to know more.