Location: Pune

Job Type: Full-time

Experience Required: 0-3 years

Salary Range: 5-8 LPA

We are looking for an AI Engineer with strong technical expertise in developing intelligent, data-driven and generative AI systems.

The ideal candidate will thrive in a fast-paced startup environment, collaborating with cross-functional teams to design, build, and deploy AI-powered solutions using LLMs, embeddings, vector databases and modern AI frameworks.

Responsibilities

• Design and build AI-native products using LLMs, agentic architectures and modern orchestration frameworks

• Develop and optimize RAG pipelines using embeddings, vector databases, semantic retrieval, and contextual memory systems

• Build autonomous and semi-autonomous AI agents capable of tool use, reasoning, workflow execution, and multi-step decision making

• Implement MCP (Model Context Protocol) based integrations and context-aware AI systems

• Create production-grade workflows using LangGraph, LangChain, Semantic Kernel, CrewAI, AutoGen, or similar orchestration frameworks

• Integrate AI systems with APIs, enterprise platforms, databases, ecommerce systems, CRMs, and external tools

• Work on prompt engineering, structured outputs, evaluation pipelines, and agent optimization strategies

• Build observability, tracing, and evaluation systems using Langfuse, LangSmith, Helicone, or equivalent AI monitoring platforms

• Develop scalable backend services and APIs for AI-powered applications

• Collaborate with frontend and product teams to create seamless AI-first user experiences

• Optimize latency, token usage, reliability, and inference performance across AI workflows

• Participate in architecture discussions, experimentation, rapid prototyping, and production deployments

Required Skills & Qualifications

• Bachelor's degree in Computer Science, Engineering, AI, or equivalent practical experience

• Strong understanding of machine learning, deep learning, NLP, and LLM fundamentals

• Hands-on experience with modern AI application frameworks

• Strong experience with LangChain, LangGraph, or similar AI orchestration frameworks

• Practical experience building RAG pipelines, embeddings workflows, semantic search systems, and contextual retrieval architectures

• Experience working with MCPs, AI tool ecosystems, and context-aware agent systems

• Familiarity with vector databases such as Pinecone, ChromaDB, Weaviate, Qdrant, or Milvus

• Experience integrating and working with LLM APIs such as OpenAI, Anthropic, Google Vertex AI, Azure OpenAI, or AWS Bedrock

• Strong understanding of agentic workflows, multi-agent systems, function calling, tool use, memory management, and autonomous execution patterns

• Experience with observability and AI evaluation platforms such as Langfuse, LangSmith, Helicone, Arize, or Weights & Biases

• Strong backend engineering skills with APIs, microservices, asynchronous systems, and cloud-native architectures

• Familiarity with Docker, Kubernetes, CI/CD pipelines, and scalable deployment practices

• Ability to work on data preprocessing, transformation, chunking, indexing, and model readiness workflows

• Strong analytical, debugging, optimization, and performance tuning skills for AI systems

• Excellent communication and collaboration skills in a startup-like, multi-disciplinary environment

Preferred (Nice-to-Have)

• Experience fine-tuning and deploying open-source LLMs

• Familiarity with AI orchestration and agent frameworks

• Exposure to memory architectures, knowledge graphs, hybrid retrieval, graph RAG, and long-context optimization strategies

• Experience building AI copilots, conversational interfaces, AI assistants, or workflow automation products

• Knowledge of frontend technologies such as React, Next.js, TypeScript, or Flutter for AI-native product development

• Understanding of AI security, guardrails, prompt injection prevention, and responsible AI practices

• Familiarity with streaming architectures, real-time event systems, and async processing patterns

• Experience with cloud AI infrastructure on AWS, Azure, or Google Cloud Platform

• Experience with evaluation frameworks, prompt testing, synthetic datasets, and AI benchmarking methodologies

• Understanding of AI UX patterns and human-in-the-loop workflows

• Experience with Agile/Scrum workflows, Git, and collaborative engineering practices

What We are Looking for

• Builders who are excited about shipping real AI products, not just prototypes

• Engineers who think in systems, workflows, automation, and scalable architectures

• Curiosity about emerging AI tooling, agentic systems, and rapid experimentation

• Strong ownership mindset with the ability to work in a fast-moving product environment

• Passion for creating practical AI experiences that solve real business problems

Why Join Incerro

• Opportunity to work on cutting-edge AI-native products and agentic systems

• High ownership and fast execution environment

• Exposure to modern AI stacks, orchestration frameworks, and enterprise AI implementations

• Work closely with leadership, product teams, and global clients

• Opportunity to shape the future direction of AI-driven platforms and products

AI Native Product Engineer