AI/ML Engineer (Python • FastAPI • RAG • LLMs)

Job Description: AI/ML Engineer (Python • FastAPI • RAG • LLMs)*

*Position:* AI/ML Engineer

*Experience:* 5+ Years

*Location:* Remote/Hybrid/On-site (as per company policy)

*Employment Type:* Full-time

### *Overview*

We are seeking a highly skilled *AI/ML Engineer* with strong expertise in *Python, FastAPI, LLM frameworks, RAG systems, data processing, and **vector databases* to build scalable AI-driven products and automation tools. The ideal candidate should have hands-on experience in *LLM orchestration, data pipelines, text analytics, and **machine learning research & development*.

---

## *Key Responsibilities*

### *AI / LLM Development*

* Design and develop *LLM-powered applications* using *LangChain, LlamaIndex*, and other AI orchestration tools.

* Implement *Retrieval-Augmented Generation (RAG)* pipelines using vector databases such as *Pinecone, Weaviate, Qdrant, Milvus, or ChromaDB*.

* Fine-tune open-source LLMs and optimize inference pipelines.

### *Backend Engineering*

* Build scalable *REST APIs* and microservices using *FastAPI*.

* Integrate AI/ML models into production-grade backend systems.

### *Data Engineering & Scraping*

* Develop reliable *web data scraping* tools using Python and modern scraping frameworks.

* Build *data ingestion pipelines* for structured and unstructured content.

* Implement robust *data cleaning, text preprocessing, and regex-based extraction techniques*.

### *Machine Learning R&D*

* Conduct research, experiment with ML algorithms, and improve model performance.

* Evaluate, benchmark, and prototype new LLM and RAG techniques.

### *Databases*

* Manage and optimize *MongoDB* collections for high-performance storage.

* Implement embeddings storage and search using *vector databases*.

### *Testing & Quality Assurance*

* Write automated test cases using *Pytest* for APIs, ML logic, and data pipelines.

* Ensure system reliability through CI/CD integration and code quality standards.

---

## *Required Skills*

### *Core Skills*

* Strong proficiency in *Python*.

* Experience with *FastAPI, **Pytest*, and modern backend development practices.

* Practical knowledge of *LangChain, LlamaIndex*, and RAG architecture.

* Hands-on experience using vector databases (Pinecone, Qdrant, Milvus, etc.).

* Expertise in *text processing, NLP pipelines, embeddings, and regex*.

* Knowledge of *LLMs*, prompt engineering, and model deployment.

### *Additional Skills*

* Experience in *data scraping* (BeautifulSoup, Selenium, Playwright, etc.).

* Familiarity with *MongoDB* and NoSQL data modeling.

* Understanding of *ML research methodologies*, model evaluation, and optimization.

---

## *Nice-to-Have*

* Knowledge of *Docker, **Kubernetes*, or cloud platforms (AWS/GCP/Azure).

* Experience with *model fine-tuning* (LoRA, QLoRA).

* Exposure to GPU optimization/frameworks like *PyTorch or TensorFlow*.

---

## *Education*

* Bachelor's or Master's degree in Computer Science, AI/ML, Data Science, or a related field (or equivalent practical experience).

---

## *Why Join Us*

* Work with cutting-edge AI/ML technologies.

* Opportunity to innovate and build large-scale AI solutions.

* Collaborative and growth-focused environment.

Job Type: Contractual / Temporary
Contract length: 3 months

Pay: ₹24,746.91 - ₹153,917.36 per month

Work Location: In person