Gen AI Engineer - LLM/RAG
First seen by Alion on Oct 30, 2026.
WE ARE HIRING | GEN AI ENGINEER
Location: Pune / Gurugram
Experience: 5 - 7 Years
Work Mode: Hybrid
CTC:?16 - 22 LPA
Note: This is one of the stronger production-oriented Gen AI opportunities, not just a prompt-engineering or chatbot-development role.
Key Responsibilities:
- Design, develop, and implement production-ready Gen AI / LLM-based applications.
- Build and optimize RAG pipelines using embeddings and vector databases.
- Develop prompt engineering solutions and integrate LLM APIs.
- Work with frameworks such as LangChain and LlamaIndex.
- Debug, enhance, and maintain existing Gen AI platforms and codebases.
- Build reusable Gen AI frameworks, workflows, and AI agent configurations.
- Collaborate directly with clients on technical and business requirements.
- Support application deployment, monitoring, and optimization.
Required Skills:
- Strong hands-on Python programming experience.
- Practical experience in Generative AI and LLM application development.
- Expertise in Prompt Engineering and OpenAI / Anthropic APIs.
- Hands-on experience with RAG, embeddings, and vector databases.
- Knowledge of LangChain or LlamaIndex.
- Good understanding of Git, testing, and software engineering practices.
Good to Have:
- Experience with AWS cloud services.
- Kubernetes / EKS and containerization.
- SQL / NoSQL databases.
- CI/CD pipelines and deployment automation.
- Experience building reusable Gen AI authoring frameworks and AI agents.
Ideal Candidate:
We are looking for a hands-on Gen AI Engineer with strong development expertise, production-level implementation experience, debugging capabilities, and good client-facing communication skills.
Interested candidates can share their updated CV at & Email Subject: Gen AI Engineer
Skills
Generative AI, Python, LangChain, RAG, Prompt Engineering, Machine Learning, Agentic AI, AWS