Generative AI Engineer- STL, Pune

Prodapt Solutions; Pune District; On-site; INR 1,800,000 - 2,800,000; Full time

Job summary

Prodapt Solutions invites applications for a Generative AI Engineer to design, build, and deploy LLM-powered applications and autonomous AI systems. You will work closely with product, data, and engineering teams to turn foundation models into reliable, scalable, production-grade solutions.

In Pune, India, you will focus on Python development, REST APIs, and practical work with LLMs, vector databases, and RAG pipelines to deliver enterprise-ready solutions in a fast-paced setting.

Qualifications

• Bachelor's or Master's degree in CS, Engineering, Data Science, or related field.
• 3+ years of software development experience with Python (OOP, async, packaging, pytest).
• Hands-on experience building LLM-powered apps via APIs (OpenAI, Anthropic, Azure OpenAI, Hugging Face).
• Experience with Agentic AI concepts: tool calls, ReAct reasoning, multi-agent orchestration, memory management.
• Familiarity with RAG architecture and vector databases (FAISS, Pinecone, Weaviate, Chroma, pgvector).
• REST API development, Docker, and cloud platforms (AWS, Azure, or GCP).

Responsibilities

• Design and build LLM-powered applications and autonomous AI workflows.
• Implement RAG pipelines including ingestion, embedding, vector search, and re-ranking.
• Write clean, modular Python code for data processing, API services, and model integration.
• Build and expose APIs (FastAPI or Flask) for LLM-based services and integrate with enterprise systems.
• Fine-tune or adapt models using LoRA/QLoRA and instruction tuning where justified.
• Design prompts, evaluation harnesses, and guardrails to improve output quality and safety.

Skills

Python

LLMs

REST API

Docker

NLP fundamentals

Problem-solving

Education

Bachelors or Masters in CS/Engineering/Data Science

Tools

FAISS

Pinecone

Weaviate

Chroma

pgvector

Job description

About the Role:-

We are looking for a Generative AI Engineer to design, build, and deploy LLM-powered applications and autonomous agentic AI systems. You will work closely with product, data, and engineering teams to turn foundation models into reliable, scalable, production-grade solutions.

Key Responsibilities:-

• Design and build applications on top of Large Language Models (open-source and proprietary, such as GPT, Claude, Llama, Mistral, and Gemini).
• Develop agentic AI workflows where LLMs plan, reason, call tools, and execute multi-step tasks using frameworks such as LangChain, LangGraph, LlamaIndex, or CrewAI.
• Implement Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embedding generation, vector search, and re-ranking.
• Write clean, modular, and well-tested Python code for data processing, API services, and model integration.
• Build and expose APIs (FastAPI or Flask) for LLM-based services and integrate them with enterprise systems.
• Fine-tune or adapt models using techniques such as LoRA/QLoRA and instruction tuning when task requirements justify it.
• Design prompts, evaluation harnesses, and guardrails to improve output quality, safety, and reliability.
• Monitor model performance, latency, cost, and hallucination rates in production; iterate based on metrics.
• Collaborate with product managers, data scientists, and DevOps engineers to define requirements and ship features.
• Stay current with advances in LLMs, agent architectures, and GenAI tooling, and share learnings with the team.

Required Skills and Qualifications:-

• Bachelors or Masters degree in Computer Science, Engineering, Data Science, or a related field.
• 3+ years of software development experience, with strong proficiency in Python (OOP, async programming, packaging, testing with pytest).
• Hands-on experience building applications with LLMs via APIs (OpenAI, Anthropic, Azure OpenAI, Hugging Face, or similar).
• Practical experience with Agentic AI concepts: tool/function calling, ReAct-style reasoning, multi-agent orchestration, and memory management.
• Working knowledge of RAG architecture and vector databases (FAISS, Pinecone, Weaviate, Chroma, or pgvector).
• Experience with prompt engineering and evaluation of LLM outputs (e.g., RAGAS, DeepEval, or custom metrics).
• Familiarity with REST API development, Docker, and cloud platforms (AWS, Azure, or GCP).
• Solid understanding of NLP fundamentals, embeddings, and transformer architectures.
• Strong problem-solving skills and the ability to communicate technical trade-offs clearly.