AI Engineer Agentic, Generative AI
Skills
About the role
This is a full-time AI engineering role for a software engineer with three to five years of experience, listed in Pune. You will build agentic workflows, retrieval systems, LLM integrations, data pipelines, and production-quality Python solutions. The role combines applied generative AI development with testing, analytics, and client-oriented delivery practices.
What you’ll do
- Build agent workflows with tools, memory, planning loops, and MCP connections.
- Create ingestion, chunking, embedding, retrieval, and evaluation pipelines.
- Integrate LLM APIs with prompts, function calls, structured outputs, and context handling.
- Use AI coding assistants and validate their output.
- Develop maintainable Python applications using established design principles.
- Write unit and integration tests using a test-driven approach.
- Build data ingestion and transformation pipelines with Python, NumPy, and pandas.
- Analyze data and create visualizations.
- Support data-quality and transformation work.
- Participate in reviews, Agile ceremonies, and Git-based delivery.
What they’re looking for
- Three to five years of software engineering experience with strong Python fundamentals.
- Hands-on use of an agentic framework such as LangChain, LangGraph, AutoGen, CrewAI, or an equivalent.
- Experience integrating a major LLM provider.
- Working knowledge of RAG, embeddings, vector stores, and retrieval evaluation.
- Familiarity with MCP and agentic workflow patterns.
- Strong, systematic prompt-engineering skills.
- Knowledge of SOLID principles, design patterns, clean code, and testing.
- NumPy, pandas, and at least one visualization library.
- Foundational understanding of model training, data preparation, and fine-tuning.
- Git, an IDE such as VS Code, Agile or Scrum, and clear technical communication.
Nice to have
- The posting does not identify separate preferred qualifications.
What’s on offer
- Full-time employment in Pune.
- Competitive salary and professional development opportunities.
- The posting does not state a salary figure, remote arrangement, visa sponsorship, or relocation support.
Questions about this role
How much experience is required for this AI Engineer role?
The posting asks for three to five years of software engineering experience.
Which agentic AI frameworks are mentioned?
LangChain, LangGraph, AutoGen, CrewAI, or an equivalent framework.
Does the role require RAG experience?
Yes. The posting requires familiarity with chunking, embeddings, vector stores, and retrieval evaluation.
Which programming language is central to the role?
Python is the primary programming language.
Related roles
Software Engineer (AI-Powered Advertising Agents - AgenticOS)
A software engineering role at PubMatic in Pune building AI agents for programmatic advertising, open to candidates with 2-10 years of experience.
Principal Engineer - Gen AI, LLM, RAG, Agentic AI
A principal engineering role at Wells Fargo in Bengaluru focused on GenAI, RAG and agentic AI architecture, evaluation and governance. Suited to a senior technical leader with deep GenAI stack and AI security expertise.
AI Business Solutions – AI Engineer Senior
A senior AI engineer role at EY building agent-based solutions on Microsoft AI technologies, based in Bengaluru.
IN_Senior Associate_Azure AI/ML/Agentic AI Engineer_GCC_Advisory_Bangalore
An on-site Bengaluru role building agentic AI and RAG applications on the Azure AI stack at PwC's Advisory GCC. Suited to a Python engineer with 4-8 years of experience in Azure AI and agentic frameworks.
IN_Senior Associate_Azure AI/ML/Agentic AI Engineer_GCC_Advisory_Bangalore
An on-site Bengaluru role building agentic AI and RAG applications on the Azure AI stack at PwC's Advisory GCC. Suited to a Python engineer with 4-8 years of experience in Azure AI and agentic frameworks.
AI Engineer – Generative AI
Onsite AI Engineer role in Hyderabad, Ahmedabad, or Indore building generative-AI and agentic systems. The position suits an engineer with at least six years of experience across LLMs, RAG, Python, and cloud deployment.