Senior Artificial Intelligence Engineer

Sunovaa Tech; Pune District; On-site; INR 1,600,000 - 2,600,000; Full time

Job summary

Sunovaa Tech is seeking a skilled software engineer to design, develop, and deploy production-grade AI and GenAI solutions using Python, LLMs, NLP, and RAG in Pune, India. You will build scalable retrieval architectures with vector search and hybrid retrieval, optimize RAG pipelines, and implement structured prompt engineering to improve quality and reduce hallucinations.

You will also design automated evaluation methods, develop AI services and APIs with FastAPI and Docker, and follow SDLC

Qualifications

• 5+ years in software engineering with AI, NLP, IR or GenAI.
• Proficient in Python and building production-grade software.
• Experience deploying LLM and RAG-based applications in enterprise environments.
• Strong understanding of NLP, LLMs, embeddings, vector search and retrieval architectures.
• Hands-on with RAG, hybrid retrieval, vector databases/search platforms, GraphRAG preferred.

Responsibilities

• Design, develop, and deploy production-grade AI/GenAI solutions using Python, LLMs, NLP, and RAG.
• Build scalable retrieval architectures with vector search and hybrid retrieval.
• Develop and optimize RAG pipelines using OpenSearch and vector databases.
• Implement structured prompt engineering to improve response quality and reduce hallucinations.
• Design automated evaluation to benchmark LLM quality and retrieval performance.
• Develop AI services and APIs using Python, FastAPI, Docker, and modern software practices.
• Write clean, typed Python code with unit tests and code-quality practices.
• Follow SDLC, Git workflows, CI/CD, testing, and production deployment.
• Collaborate with Data Scientists, Software Engineers, and stakeholders to productionize AI experiments.
• Continuously evaluate emerging GenAI technologies and deliver value.

Skills

Python

LLMs & RAG

NLP & IR

Vector search

OpenSearch

FastAPI

Docker & CI/CD

Testing (pytest)

Git & SDLC

Tools

OpenSearch

Vector databases

GraphRAG

AWS Bedrock / Azure OpenAI

CI/CD tooling

Job description

Role & Responsibilities

• Design, develop, and deploy production-grade AI and Generative AI solutions using Python, LLMs, NLP, and Retrieval-Augmented Generation (RAG).
• Build scalable retrieval architectures using vector search, hybrid retrieval, and other information retrieval techniques.
• Develop and optimize RAG pipelines using technologies such as OpenSearch and vector databases.
• Implement structured prompt engineering and LLM-based solutions to improve response quality, relevance, and reduce hallucinations.
• Design automated evaluation approaches to benchmark LLM output quality and retrieval performance.
• Develop reliable AI services and APIs using Python, FastAPI, Docker, and modern software engineering practices.
• Write clean, maintainable, typed and testable Python code with appropriate unit testing and code-quality practices.
• Follow SDLC best practices including Git workflows, code reviews, CI/CD, testing, and production deployment.
• Work closely with Data Scientists, Software Engineers, and business stakeholders to convert AI experiments into reliable production solutions.
• Continuously evaluate emerging GenAI technologies and apply practical solutions that deliver measurable business value.

Preferred Candidate Profile

• 5+ years of experience in software engineering with strong experience in AI, NLP, Information Retrieval, or Generative AI.
• Strong hands‑on expertise in Python and experience developing production-grade software applications.
• Proven experience building and deploying LLM and RAG-based applications in enterprise environments.
• Strong understanding of NLP, LLMs, Prompt Engineering, embeddings, vector search, and retrieval architectures.
• Hands‑on experience with RAG, hybrid retrieval, vector databases/search platforms, and preferably GraphRAG.
• Experience with OpenSearch or similar vector/search technologies is highly desirable.
• Experience with FastAPI, Docker, Git, CI/CD, pytest, and modern Python development practices.
• Experience with AI evaluation methodologies or automated pipelines for measuring LLM and retrieval quality.
• Exposure to AWS Bedrock, Azure OpenAI, or similar cloud-based AI platforms is an advantage.
• Knowledge of MCP (Model Context Protocol) and modern API standards is a plus.
• Strong analytical and logical reasoning skills with the ability to solve complex AI problems.
• Strong communication skills with the ability to work effectively with both technical and non-technical stakeholders.
• Hands‑on, adaptable, pragmatic, and ownership-driven approach to solving business problems.